create-tool

name	create-tool
description	ALWAYS use this skill when the user asks to build, modify, or audit a FrontMCP tool. Covers everything inside `@Tool({...})`: class and function-style tools, Zod input/output schemas with derived `execute()` types, dependency injection (`this.get` / `this.tryGet`), error handling (`this.fail`, MCP error classes), throttling (rate-limit / concurrency / timeout), auth providers (single / multi / vault), availability constraints (`availableWhen`), elicitation (`this.elicit`), interactive UI widgets via `@Tool({ ui })` (MCP Apps / SEP-1865 — including `.tsx` FileSource, CSP, `window.FrontMcpBridge`, host-detect `resourceMode`), annotations (`readOnlyHint` / `destructiveHint` / …), `examples` metadata, registration in `@App({ tools })`, and per-tool unit testing. Does NOT cover: - Read-only data exposed via a URI — use `create-resource` - Conversation templates / system prompts — use `create-prompt` - Multi-tool orchestration loops — use `create-agent` - Background work / pipelines — use `create-job` / `create-workflow` - Server-level config (transport, sessions, auth modes) — use `config` / `auth` Triggers: `@Tool`, ToolContext, tool decorator, MCP tool, snake_case tool name, inputSchema, outputSchema, ToolInputOf, ToolOutputOf, `@Tool({ ui })`, tool UI widget, MCP Apps widget, FileSource widget, `.tsx` widget, ui.csp, ui.resourceMode, window.FrontMcpBridge, tool annotations, readOnlyHint, destructiveHint, rate-limit tool, throttle tool, concurrency tool, tool timeout, this.fail, this.respond, this.fetch, this.notify, this.progress, this.elicit, ElicitationDisabledError, ToolContext.execute, this.get(TOKEN), this.tryGet, register tool in @App, tool examples metadata, availableWhen, missingAxes, `tool()` function builder, Tool.esm, Tool.remote, PublicMcpError, ResourceNotFoundError, MCP_ERROR_CODES, ui://widget.
when_to_use	Trigger when creating or editing a `*.tool.ts` / `*.tool.tsx` file, adding a `@Tool` decorator, defining `inputSchema` / `outputSchema` for a tool, deriving `execute()` parameter or return types, wiring dependency injection into a tool, returning structured / media / resource content, adding a `ui:` block (HTML / MDX / React / FileSource), configuring throttling, declaring auth providers, restricting platforms via `availableWhen`, requesting interactive input via `this.elicit`, adding tool `annotations`, or registering a tool in `@App({ tools })`.
paths	**/*.tool.ts, **/*.tool.tsx, **/tools/**/*.ts, **/apps/*/tools/**, **/*.tool.spec.ts
layout	component
license	Apache-2.0
priority	10
visibility	public
tags	["development","tool","create-tool","decorator","input-schema","output-schema","ToolContext","ui","mcp-apps","annotations","throttling","auth-providers","availability","elicitation"]
category	development/create
bundle	["recommended","minimal","full"]
allowed-tools	Read Edit Write Grep Glob Bash
metadata	{"docs":"https://docs.agentfront.dev/frontmcp/servers/tools"}

Create a FrontMCP Tool

Tools are the primary way to expose executable actions to AI clients in the MCP protocol. In FrontMCP, every tool is a TypeScript class that extends ToolContext, decorated with @Tool({...}), and registered on an @App (or directly on @FrontMcp for simple servers).

This skill is the single source of truth for building tools. It owns:

• The @Tool decorator surface
• Input / output schemas and how to derive execute() types from them
• Dependency injection, error handling, progress / notifications
• Throttling: rate-limit, concurrency, timeout
• Auth providers and the credential vault
• Platform / runtime / surface availability constraints
• Elicitation (interactive input mid-execution)
• Tool UI widgets — the ui: block, MCP Apps / SEP-1865, .tsx FileSource, CSP, window.FrontMcpBridge
• Annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
• The examples metadata field
• Function-style tools, remote / ESM tools
• Registration patterns
• Per-tool unit testing

For everything else — resources, prompts, agents, jobs, workflows, adapters, plugins, providers, channels — use the matching create-<thing> skill.

First time? Start with references/quick-start.md, then jump to the example matching your scenario via the Decision Tree below.

---

Inherited defaults

This skill ALWAYS applies these defaults — never opt out without an audited reason:

Default	Source	What it enforces
inputSchema is a Zod raw shape	rules/input-schema-is-raw-shape.md	Plain object mapping field → Zod type. Framework wraps internally. Never at the top level.