semantic-model-authoring

name

semantic-model-authoring

description

Author and inspect Power BI semantic models and their metadata: list tables, columns, measures, relationships; create, edit, deploy, refresh, and manage models; optimize DAX; build Import, DirectQuery, and Direct Lake models; configure data sources, permissions, connections; and prepare for AI/Copilot. Load this skill before acting on any semantic model authoring, metadata, or read-only inspection request: it picks the correct tool and method for the environment and permissions. Authoring-scoped: does not answer natural-language or data questions about a model's data. Does NOT author report visuals, manage workspaces, or manage RLS/OLS roles. Triggers: "create or edit a semantic model", "create or edit a DAX measure", "discover semantic model metadata", "list tables, columns, or measures in a semantic model", "refresh semantic model", "deploy semantic model to Fabric", "prepare semantic model for AI/Copilot", "set semantic model permissions".

Telemetry — MANDATORY. Every api.fabric.microsoft.com call must carry x-ms-fabric-skill: semantic-model-authoring (az rest: --headers "x-ms-fabric-skill=semantic-model-authoring"), including every LRO poll, fabric_lro and retry. Snippets omit it — add it anyway.

CRITICAL NOTES

1. To find the workspace details (including its ID) from workspace name: list all workspaces and, then, use JMESPath filtering
2. To find the item details (including its ID) from workspace ID, item type, and item name: list all items of that type in that workspace and, then, use JMESPath filtering
3. Always consider the Tool selection priority when choosing which tool to use for each operation. Do not default to TMDL edits or az rest if MCP is available and connected to the target model.

Power BI Semantic Model Authoring — CLI Skill

Workflow Selector

Use this decision tree to route to the correct workflow based on user intent:

User wants to...	Workflow
Create a semantic model from scratch	Create new semantic model
Inspect or discover model metadata (tables, columns, measures, relationships)	Discover Semantic Model Metadata
Add/edit semantic model objects (e.g. measures, tables, columns, relationships)	Modify an Existing Model
Write or refactor DAX code	Modify an Existing Model
Improve DAX query or measure performance	Optimize DAX Performance
Analyze semantic model against best practices	Analyze Best Practices
Prepare a semantic model for AI consumption (Copilot / Data Agents)	Semantic Model AI Readiness
Deploy a model to a Fabric workspace	Deploy to Fabric
Refresh a semantic model	Refresh Semantic Model
Configure data sources, parameters, or permissions	Manage Semantic Model in Fabric
Bind a semantic model to a Fabric connection (or unbind)	Bind Semantic Model to a Connection
Export / Get semantic model definition as PBIP	Export to PBIP

Table of Contents

Load these references on demand when a workflow step requires them. Do not load all at once.

Topic	Reference	When to load
Modeling Best Practices	modeling-guidelines.md	Before creating or editing any model
Naming Conventions	naming-conventions.md	When naming or renaming tables, columns, measures
Direct Lake Modeling	direct-lake-guidelines.md	When model connects to OneLake
TMDL Editing	tmdl-guidelines.md	Before generating or editing any TMDL file
PBIP Projects	pbip.md	When working with PBIP folders
DAX Language	dax-guidelines.md	When writing or reviewing any DAX code
Metadata Discovery (DAX INFO functions)	metadata-discovery.md	When discovering model metadata via DAX INFO functions (see Workflow: Discover Semantic Model Metadata)
DAX Performance Decision Guide	dax-perf-decision-guide.md	Start here when optimizing DAX
DAX Performance Pattern Catalog	dax-perf-patterns.md	Load on demand after the decision guide identifies candidate patterns
Semantic Model AI Readiness	semantic-model-ai-readiness.md	When preparing a model for Copilot or Data Agents
Semantic Model REST API	semantic-model-rest-api.md	When using az rest for TMDL CRUD, refresh, parameters, permissions, or property retrieval
Connection Binding	connection-binding.md	When binding/unbinding a semantic model to a Fabric data connection (gateway, cloud, VNet, automatic, none)
Finding Workspaces/Items	COMMON-CLI.md

---

Tool Selection Priority

Priority order (highest first):

1. Tier 1 — powerbi-modeling-mcp MCP is registered -> Use MCP for authoring (new or edit) operations against the model from any source: Power BI Desktop, Fabric workspace, or local PBIP folder. MCP is the most reliable and full-featured way to edit semantic models, with immediate effect on the live model and no risk of TMDL desync.

   Important: In case of dynamic search tools is available (e.g. tool_search_tool_regex) search for an available MCP server matching the pattern powerbi-modeling-mcp.

   This includes BOTH writes AND reads/inspection.

   • To inspect or verify changes -> use the corresponding MCP operations (List / Get).
   • Anti-pattern: opening, view-ing, glob-ing or otherwise reading TMDL files (*.tmdl) while MCP is connected. The MCP-loaded model is the source of truth - the on-disk TMDL is stale. The only exceptions is when the user explicitly asks to work with the TMDL files.

2. Tier 2 — MCP not registered + PBIP folder or Fabric workspace -> Edit TMDL files directly. Load tmdl-guidelines.md and pbip.md. When the source is a Fabric workspace, use az rest to round-trip the TMDL (load semantic-model-rest-api.md): getDefinition -> edit TMDL locally -> updateDefinition.

Fallback — none of the above available (e.g., Power BI Desktop with no PBIP and no MCP) -> STOP. The agent cannot author the model in this configuration. Instruct the user to either (a) install and register the powerbi-modeling-mcp MCP server, or (b) save the PBIX as a PBIP project, then restart the workflow.

All workflows below are tool-agnostic. Workflow steps describe the intent (connect, create, edit, save, deploy, refresh). The tool used to perform each step is determined here. Always select the highest-priority tool available for the current environment; do not mix tools when a higher-priority option works. Some workflows OVERRIDE this default priority, always check the workflow's own tool-selection rules before defaulting to Tier 1.

Connecting to a Semantic Model

A semantic model can live in three locations. Resolve the connection per Tool Selection Priority:

• Power BI Desktop: Locate the running Power BI Desktop instance and connect to its local model.
• Fabric workspace: First, find the workspace and semantic model using the Finding Workspaces and Items pattern: list workspaces to resolve the workspace ID by name, then list items of type SemanticModel in that workspace to resolve the model ID by name. Then connect to the model (live) or export its TMDL definition for local editing.
• PBIP project: Connect to the [Name].SemanticModel/definition folder. Load pbip.md to understand the PBIP folder structure - only load the [Name].SemanticModel/definition folder that includes the TMDL code.

Saving Changes to a Semantic Model

How changes are persisted depends on where the model lives and which tool tier (per Tool Selection Priority) is in use:

Live connection (Tier 1 - MCP against Desktop or Fabric workspace):

• Changes are applied immediately as each operation executes against the live model. No explicit save step is needed.
• PBIP project (live via MCP): Serialize the model back to the [Name].SemanticModel/definition folder at the end of the session. If the PBIP folder does not exist yet, follow Export to PBIP to create the full structure first.

Local TMDL editing (Tier 2 - direct file edits or az rest round-trip):

• PBIP project: Changes are already written to the TMDL files during editing. No additional save step is needed.
• Fabric workspace: Changes were made to local TMDL files exported from the service. Re-deploy the model (load semantic-model-rest-api.md for the updateDefinition flow) to push changes back to the workspace.

---

Workflow: Create new Semantic Model

When this applies: User asks to create a new semantic model from scratch.

Steps:

1. Gather requirements - interview the user until both reach a shared understanding of: purpose of the model, data source connection details and schemas, and key business entities/facts. If data source information is not available, STOP and use ask_user. Do not guess or fabricate.

2. Determine storage mode - data source is Fabric OneLake -> Direct Lake; otherwise default to Import. Only use DirectQuery when the user explicitly asks for it.

3. Design star schema - identify fact and dimension tables and relationship keys.

   • If fact table includes date field(s), create a separate date dimension table and link it to the fact with a relationship. If not explicitly requested, use PowerQuery/M partition instead of DAX calculated table.

4. Load applicable guidelines - MANDATORY: load modeling-guidelines.md before building any object (including the Tier 1 MCP path below); also load direct-lake-guidelines.md if Direct Lake. Don't build from memory.

5. Build - follow Tool Selection Priority: prefer the modeling MCP to build the whole model when one is available; otherwise use the TMDL code-edit path. Create an empty database (compatibility level 1702+), then for each table follow the execution order from Modify an Existing Model (partitions -> columns -> relationships -> measures). Storage-mode specifics:

   • Import / DirectQuery - create M parameters for the data source (Server, Database, ...) and reference them in partition M code; ensure proper dataType and sourceColumn mapping on columns.
   • Direct Lake - create a shared named expression for the Direct Lake connection using the AzureStorage.DataLake connector; use EntityPartitionSource with directLake mode mapped to the lakehouse table columns.

   Build the whole model in one pass, then deploy once. Add every table, column, relationship and measure before deploying - don't deploy a partial model and edit-redeploy. On the MCP path, keep the model in the session end to end.

---

Workflow: Discover Semantic Model Metadata

When this applies: User asks to inspect, list, or discover the model's structure - tables, columns, measures, relationships, hierarchies, partitions, roles, or storage internals. Also used internally by other workflows (Modify, Analyze Best Practices, AI Readiness) to inventory the model before editing.

Scope: This workflow covers metadata discovery only. To answer natural-language/data questions against the model, use the FabricIQ skill instead.

Pick a discovery method (highest priority first):

1. powerbi-modeling-mcp TOM inspection (List / Get) - the default when powerbi-modeling-mcp is registered and connected to the target model with Write access. It returns the structured object model directly and stays in sync with pending edits, so it is preferred while authoring.

2. DAX INFO functions - query the model's INFO.VIEW.* / INFO.* metadata rowsets. MANDATORY: before writing or running ANY INFO-function DAX, you MUST load metadata-discovery.md first. Do NOT compose INFO queries from memory; load the reference and use its patterns. Prioritize this method when any of the following is true:

   • You lack Write permission on the model. powerbi-modeling-mcp operations require Write access; with Read or Build access, use INFO functions.
   • powerbi-modeling-mcp is not registered or not available in the current environment.

   Execute the INFO-function DAX through one of these tools (highest priority first):

   • FabricIQ ExecuteQuery - requires only Read permission on the model. Load the FabricIQ skill for artifact discovery (DiscoverArtifacts) and execution mechanics.
   • powerbi-modeling-mcp dax_query_operations - requires Write permission. Use this when the modeling MCP is already connected with Write access.

Do NOT use FabricIQ GetSemanticModelSchema for authoring metadata discovery - it is a data-consumption tool that can return stale metadata and miss recent edits. Even when FabricIQ is available, always use the INFO functions (via ExecuteQuery); they query the live model.

Start narrow: run the scope-estimation and INFO.VIEW.* queries first, then project/filter to only the objects relevant to the task (see metadata-discovery.md).

---

Workflow: Modify an Existing Model

When this applies: User asks to add/edit/remove measures, tables, columns, relationships, write DAX code, refactor with UDFs, or edit TMDL directly.

Steps:

1. Connect & discover - per Connecting to a Semantic Model and Discover Semantic Model Metadata. List tables, relationships, existing measures, and identify storage mode (it dictates which guidelines apply).
2. Load applicable guidelines - modeling-guidelines.md always; direct-lake-guidelines.md if Direct Lake; tmdl-guidelines.md when editing TMDL directly; dax-guidelines.md for any DAX changes (includes UDF refactoring).
3. Plan changes - identify exactly what to add, modify, or remove. Check for naming conflicts and duplicates.
4. Execute in correct order:
   • Adding tables - partitions -> columns -> relationships -> measures.
   • Adding relationships - ensure key columns exist on both sides with matching data types;
   • Adding measures - verify referenced columns/tables exist;
5. Save & validate - per Saving Changes to a Semantic Model and Validation Checklist.

---

Workflow: Optimize DAX Performance

When this applies: User asks to improve DAX query performance, diagnose slow measures, or optimize calculations.

Hard requirement: Requires a trace-capable client (MCP preferred))

Load dax-perf-decision-guide.md first and follow the framework defined there. Load dax-perf-patterns.md only when applying candidate optimization patterns. The framework includes:

1. Tier model for categorizing optimization effort
2. Trace diagnostics to identify bottlenecks
3. Pattern catalog with candidate optimization techniques to test and validate

---

Workflow: Analyze Best Practices

When this applies: User asks to review, audit, or analyze a semantic model against best practices.

Steps:

1. Connect & inventory - per Connecting to a Semantic Model and Discover Semantic Model Metadata. Capture all tables, columns, relationships, measures, and storage mode.
2. Load applicable guidelines - modeling-guidelines.md always; direct-lake-guidelines.md if Direct Lake; naming-conventions.md when assessing naming; dax-guidelines.md when assessing DAX.
3. Evaluate - compare the model against the loaded guidelines (star schema, naming, relationship cardinality and cross-filter, explicit measures with formatString, column data types and sourceColumn, hidden FK columns, calculated-column-vs-measure choices, Direct Lake constraints, etc.).
4. Present findings grouped by severity (critical, recommended, optional). For each item state the rule violated and the proposed fix. Wait for user approval.
5. Apply approved fixes via Modify an Existing Model.
6. Save & validate - per Saving Changes to a Semantic Model and Validation Checklist.

---

Workflow: Semantic Model AI Readiness

When this applies: User asks to make a semantic model ready for Microsoft Fabric Copilot, a Power BI Data Agent, or any conversational BI experience. Triggers include "Copilot readiness", "AI readiness", "Prep for AI", "prepare model for Copilot".

Load semantic-model-ai-readiness.md before starting.

Steps:

1. Confirm scope & gather context - via ask_user, confirm consumption mode (reports only / conversational BI / both) and model stability per the When to Apply section. Collect business context (process, key metrics, common natural-language questions, vocabulary). Do not invent.
2. Connect & inventory - per Connecting to a Semantic Model. Capture model contents and the source location (PBIP / Fabric workspace / Desktop-only).
3. Evaluate & route - walk the Readiness Checklist in order; for each gap, classify the fix per Editing Capability (agent-editable TOM metadata vs AI-specific artifacts the user configures in the Power BI "Prep data for AI" UI).
4. Present findings grouped by severity, each tagged with routing (agent-applicable vs user-action-required). Wait for approval.
5. Apply approved changes - apply TOM metadata fixes via Modify an Existing Model; for AI instructions, AI Data Schema, and Verified Answers, instruct the user to configure them in the Power BI "Prep data for AI" UI and, only if the user agrees, offer suggestions per the readiness reference; Desktop-only PBIX -> instruct user.
6. Save, validate, recommend live testing - per Saving Changes to a Semantic Model and Validation Checklist; advise the user to test representative natural-language prompts in Copilot or the Data Agent and iterate.

---

Workflow: Export to PBIP

When this applies: User asks to export or save a semantic model to a PBIP project folder, or there is no Fabric workspace available to deploy to (e.g., after building a model in-memory).

Key fact: Exporting a model only produces the TMDL definition files. It does NOT create the surrounding PBIP folder structure (Report folder, definition.pbism, definition.pbir, .pbip entry point). The agent must scaffold these before exporting, otherwise the result cannot be opened in Power BI Desktop.

Load pbip.md before starting and follow the PBIP folder structure defined there.

Steps:

1. Determine target - via ask_user, get the target folder path and the semantic model name. If only a folder is provided, use the model's database name as the semantic model folder name.
2. Scaffold the PBIP structure - per pbip.md, ensure <Name>.SemanticModel/ (with definition/ and definition.pbism), <Name>.Report/ (with definition/ and definition.pbir using a byPath reference), and <Name>.pbip exist. Create any missing piece.
3. Export TMDL into <Name>.SemanticModel/definition/, per Tool Selection Priority:
   • Tier 1 (MCP) - use the MCP export/save operation against the live model.
   • Tier 2 (Fabric workspace, no MCP) - call getDefinition (load semantic-model-rest-api.md) and write the returned parts.
   • Local TMDL files already on disk - copy or move them into the definition/ folder.
4. Validate - confirm the definition/ folder contains at minimum model.tmdl and table .tmdl files; confirm definition.pbism, <Name>.Report/definition.pbir (with correct byPath to ../<Name>.SemanticModel), and <Name>.pbip exist and reference each other correctly.

---

Workflow: Deploy to Fabric

When this applies: User asks to deploy or publish a semantic model to a Fabric workspace.

Hard rule — this workflow OVERRIDES the default Tool Selection Priority. Do not default to MCP just because it is available. The deployment path is determined by the source of the model, not by which tools are connected. If the source is PBIP/TMDL files on disk, you MUST use the Fabric REST API even when an MCP session is active.

Decision tree (pick exactly one — top-down, first match wins):

1. Are there PBIP / TMDL files on disk that need to be deployed? -> YES — use Fabric REST API. Call az rest with createItemWithDefinition (new model) or updateDefinition (existing model). Load semantic-model-rest-api.md.
   • Rationale: deploying TMDL files directly via the Fabric API is more reliable, faster, and avoids unnecessarily loading the model into MCP only to push it back out.
   • Do NOT open the PBIP in MCP first and then deploy via MCP. That is an explicit anti-pattern for this workflow.
2. Is the model already loaded in a live MCP session (e.g., just built in-memory, or currently being edited via MCP) with no PBIP/TMDL files involved? -> Use MCP tool to deploy with the target workspace and semantic model name.
3. Is the model live in Power BI Desktop with no PBIP saved? -> Use MCP Deploy if MCP is connected to Desktop. If MCP is not available, instruct the user to save as PBIP first, then restart this workflow at step 1.

Verify deployment succeeded by listing workspace items of type SemanticModel.

Deploy exactly once; the deploy is NOT idempotent. A retried deploy creates a second model with the same name, after which the deploy fails with There are multiple datasets named '<name>'. If you hit that error, do NOT retry blindly: list the workspace's semantic models, delete every duplicate with that name, then deploy once from the clean state. If deploying a model that may already exist, delete the existing same-named model(s) before the single deploy.

---

Workflow: Refresh Semantic Model

When this applies: User asks to refresh data in a semantic model.

Refresh is only possible when working against a live model in Desktop or Fabric Service. If working with local TMDL files, deploy the model first.

Trigger a refresh per Tool Selection Priority:

• Power BI Desktop: Tier 1 (MCP) only — use the MCP Refresh operation.
• Fabric Service: Tier 1 (MCP Refresh operation) or fallback to the Power BI Enhanced Refresh API (load semantic-model-rest-api.md).

If the refresh fails with a credential error, stop immediately and instruct the user to configure the data source connections manually in Power BI Service. Do not attempt to retry or work around credential errors programmatically.

---

Workflow: Manage Semantic Model in Fabric

When this applies: User asks to configure data sources, update parameters, or manage permissions for a semantic model in Fabric Service.

Hard rule — this workflow OVERRIDES the default Tool Selection Priority. Do not default to MCP (Tier 1) prefer using az rest and REST APIs.

Data Sources & Parameters

Get/update data sources and parameters via Power BI REST API. Load semantic-model-rest-api.md.

Permissions

List/grant/update dataset user permissions via Power BI REST API. Load semantic-model-rest-api.md.

Connection Binding

Load connection-binding.md and follow it. The reference covers prerequisites, the bindConnection endpoint, the discover -> match -> bind -> validate steps, all connectivityType values, the unbind pattern, and troubleshooting.

Key rules (full details in the reference):

• Use the Fabric Bind Semantic Model Connection REST API (supersedes the legacy Power BI BindToGateway).
• One bind request per data source reference - the API does not support bulk binding.
• Discover the model's data source references via List Item Connections, then match connectionDetails against List Connections to find the target id. Create a connection first if no match exists.
• Validate by re-listing item connections and triggering a refresh.

---

Validation Checklist

Run after any model creation or modification:

Always (works with PBIP, Desktop, and Fabric Service):

1. Check the PBIP structure - if the model is sourced from a PBIP folder, ensure the folder structure and files are correct (see pbip.md).
2. Verify against modeling guidelines - re-check every change against modeling-guidelines.md (and direct-lake-guidelines.md for Direct Lake models).

Only when connected to an Analysis Services database (Power BI Desktop or Fabric Service):

3. Test new measures - for each new measure, run a simple DAX query to validate it returns expected results (e.g., EVALUATE { [Measure Name] }). Skip this step when working with local TMDL/PBIP files only.
4. Test table refresh - when new tables were created, trigger a refresh to verify that partitions, data source expressions, and column mappings are correct. A failed refresh typically indicates mismatched sourceColumn names, invalid M expressions, or incorrect Direct Lake entity references. Skip this step when working with local TMDL/PBIP files only.

If any check fails, fix the issue and re-run validation.

---

Must/Prefer/Avoid

MUST

• Understand the data source schema before starting - analyze source tables, columns, and data types before designing or modifying the model.
• Follow modeling guidelines - load modeling-guidelines.md before creating or editing any model; apply star schema design, naming conventions, and column/measure rules
• Follow Tool Selection Priority - always pick the highest-priority tool tier available for the current environment; do not mix tiers when a higher-priority option works

PREFER

• Star schema over snowflake or flat tables - denormalized dimensions with single-column relationship keys
• Consistency with existing model patterns - when editing an existing model, match its naming conventions and structure rather than imposing new ones
• TMDL format over TMSL - text-based, diff-friendly, preferred for Fabric
• Validate after changes - use Workflow: Discover Semantic Model Metadata to confirm objects landed.

AVOID

• Hardcoded workspace/item IDs - resolve dynamically via API
• Reading TMDL files when MCP is connected - view/glob on *.tmdl while a Tier 1 MCP session is live is an anti-pattern (see Tool Selection Priority).
• Hand-authoring TMDL files when MCP is registered - using create/edit/file-write tools to scaffold model.tmdl, database.tmdl, relationships.tmdl, or tables/*.tmdl is a Tier 1 anti-pattern, including for brand-new models. Build and export via MCP tools.

DENY

• Manage RLS/OLS role membership - do not propose REST calls, az rest URLs, MCP operations, or TMDL changes to add/remove users or groups from a security role. Refuse the request as out-of-scope here and redirect the user to the Power BI portal.

---

Examples

Scope note — examples use az rest for discovery to resolve ID's and discover Fabric metadata (see COMMON-CLI.md § Finding Workspaces and Items). Authoring of the semantic model definition is routed through Tool Selection Priority: Tier 1 MCP powerbi-modeling-mcp when available, Tier 2 TMDL editing via getDefinition / updateDefinition otherwise.

Example 1: Modify an Existing Semantic Model

Prompt: "Create base measures for all aggregable columns in the semantic model Sales in workspace Marketing."

Agent response - follows Workflow: Modify an Existing Model.

1. Discover IDs via az rest.
2. Connect to the model per Connecting to a Semantic Model and Tool Selection Priority. With powerbi-modeling-mcp registered, connect MCP directly to the Fabric workspace model (Tier 1). Otherwise fall back to Tier 2 (getDefinition -> edit TMDL locally).
3. Inspect & plan - list tables and columns via the active tool tier; identify aggregable columns (numeric, not foreign keys, not hidden surrogate IDs) and decide on SUM / AVERAGE / MIN / MAX per column following modeling-guidelines.md and naming-conventions.md. Load dax-guidelines.md before writing DAX.
4. Add measures per Workflow: Modify an Existing Model.
   • Tier 1 (MCP): call tool create for each new measure with expression, formatString, and target table. Do not hand-author TMDL.
   • Tier 2 (no MCP): edit the table's .tmdl file directly and round-trip via updateDefinition REST API.
5. Save & validate per Saving Changes to a Semantic Model.

---

Example 2: Create a New Semantic Model from a Fabric Lakehouse

Prompt: "Create a new Power BI semantic model in workspace Marketing, using the SalesLakehouse in the same workspace as the data source."

Agent response - follows Workflow: Create new Semantic Model.

1. Discover workspace + lakehouse IDs via az rest.
2. Discover lakehouse schema - list tables and columns via the Lakehouse OneLake APIs or the SQL Endpoint of the lakehouse. Capture table names, column names, and data types - these drive semantic model table, column definitions and partition metadata.
3. Select tool tier per Tool Selection Priority: prefer Tier 1 (powerbi-modeling-mcp) for the full build. Tier 2 (PBIP/TMDL scaffolding then deploy) only if MCP is not registered.
4. Build the model following Workflow: Create new Semantic Model - data source is OneLake so the storage mode is Direct Lake (load direct-lake-guidelines.md and modeling-guidelines.md). Design a star schema from the lakehouse tables, then:
   • Create the empty database.
   • Create one shared named expression for the lakehouse connection.
   • For each table: add EntityPartitionSource (mode directLake) -> columns mapped to lakehouse columns -> relationships -> measures.
5. Deploy per Workflow: Deploy to Fabric:
6. Validate per the Validation Checklist - confirm the model appears in the workspace and trigger an initial refresh to verify Direct Lake column mappings resolve.

---

Example 3: Bind a Semantic Model to a Fabric Connection

Prompt: "Bind semantic model Sales in workspace Marketing to the sql-prod connection."

Agent response - follows Workflow: Manage Semantic Model in Fabric § Connection Binding. No MCP - this workflow overrides Tool Selection Priority and is REST-only.

1. Discover workspace + model IDs via az rest.

2. Discover the target connection in Fabric by matching the server name:

   SERVER="sql-prod"
   CONN_ID=$(az rest --method get --resource "https://api.fabric.microsoft.com" \
     --url "https://api.fabric.microsoft.com/v1/connections" \
     --query "value[?connectionDetails.path | contains(@, '$SERVER')] | [0].id" -o tsv)
   

   If no connection matches, stop and instruct the user to create one first per connection-binding.md.

3. Execute the bind per Workflow: Manage Semantic Model in Fabric § Connection Binding - load connection-binding.md and follow the discover -> match -> bind -> validate flow:

   • List the model's data source references (List Item Connections).
   • For each reference whose connectionDetails matches $CONN_ID, call the Fabric bindConnection endpoint one request per data source reference (no bulk binding).

4. Validate - re-list item connections to confirm the binding, prompt the user to trigger a refresh per Workflow: Refresh Semantic Model. Credential errors -> stop and direct the user to the Service portal (per TROUBLESHOOTING).

---

TROUBLESHOOTING

Symptom	Fix
MCP connection failure	Fall back to TMDL editing (see Tool Selection Priority). Inform the user about the fallback.
TMDL validation errors	Read error details, fix syntax, re-validate. Load tmdl-guidelines.md.
403 Forbidden / identity None	User needs Contributor+ role - stop immediately. Do not retry.
401 Unauthorized	Correct the --resource audience once (see semantic-model-rest-api.md). If it persists after the audience is right, it is missing permissions - stop and tell the user. Do not retry-loop.
202 Accepted but no result	Poll LRO to completion.
Parts missing after updateDefinition	Must include ALL parts - modified + unmodified.
Refresh credential error	Direct user to configure in Service portal. Do not retry.
DAX errors in measures	Check column/table name references (case-sensitive). Verify referenced objects exist.
Deployment failure	Check workspace permissions, model compatibility level, and Direct Lake expression source references.
Missing data source	Verify M parameters or named expressions are correctly defined.