| name | web-research |
| description | Research a question on the open web and return a verified, cited answer. Trigger when the user asks to "look this up", "research X", "find out what/whether", "what's the latest on", or any question you can't answer reliably from memory — versions, prices, current events, docs, comparisons. Emphasizes multiple independent sources, checking dates, distinguishing primary from hearsay, and citing what you claim. |
web-research
The goal is a defensible answer, not the first plausible link. A single
source is a claim; two independent sources agreeing is evidence. Your job is to
turn a question into a small set of trustworthy findings, each traceable to
where it came from.
Use the web_search tool to find sources and web_fetch to read them in full —
snippets lie by omission; open the page before you quote it.
Loop
- Sharpen the question. What exact fact settles it? "Is library X
compatible with Y" → "does X's docs/changelog list Y support, and as of which
version". A vague question yields vague searches.
- Search deliberately. Start broad to map the terrain, then narrow with
specific terms, error strings, version numbers, or
site: filters. Rephrase
when results are thin — different words surface different sources. Prefer the
primary source: official docs, the changelog, the standard, the paper, the
vendor's own page — over a blog summarizing it.
- Open and read.
web_fetch the promising results. Read enough to confirm
the claim in context, not just a matching sentence.
- Cross-check. Confirm anything load-bearing against a second independent
source. Two blogs both citing the same original are one source. Watch for
an answer that everyone copied from one wrong post.
- Synthesize with citations. Answer the question directly, then support it
with links. Note your confidence and any disagreement you found.
