web_capture

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint; the description adds the recording window after load, the fact that bodies are off by default because they are large (a cost disclosure), and the shape of what comes back. It does not cover the `profile`/auth implications or timing/rate behaviour, so it stops short of full transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and dense with useful detail; the workflow sentence and return-shape sentence both earn their place. Slightly long and clause-heavy, but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description supplies the return contract (`endpoints` and `responses` with url, status, mime, and body when requested) plus default behaviours, so an agent has everything needed to call and interpret it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so a 3 is the baseline; the description goes beyond it by explaining the intent behind `pattern` (URL substring, omit first time), `bodies` (large, enable once the endpoint is named), and the interrogation sequence, adding real usage semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — recording JSON/XHR responses a page fetches during load and returning them — and contrasts it with the HTML-derived alternative and with link-following crawls. An agent can distinguish it from siblings like web_fetch or web_crawl without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit two-step workflow (call once without `pattern` to survey, then with `pattern` and `bodies=true` to retrieve) and a concrete selection rationale: find the real endpoint behind listing/pagination, and page=1 endpoints accept page=2, which beats following links.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.