Run site audit

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the safety profile is partly covered. The description adds real value beyond that: bounded resource use (15 pages, 15s), SSRF protection during the crawl, and the fact that a report artifact is persisted — behavior the agent could not derive from the annotations.

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?

Two sentences, both load-bearing: the first carries scope and limits, the second carries the persisted output and the exclusions. Front-loaded with the action and 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?

No output schema exists, so the description must carry the return story, and it only says a report is saved without indicating how the caller retrieves it (get_site_audit/list_site_audits) or whether the call is synchronous or async. For a crawl-and-persist tool with no output schema, that retrieval gap matters.

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 description coverage is 100%, so project_id, max_pages and idempotency_key are already documented in the schema; the baseline is 3. The description restates the 15-page cap but adds no new parameter semantics (no idempotency guidance, no note on the project_id pattern or scope enforcement).

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?

Specific verb (crawl) plus resource (project domain) plus hard scope (at most 15 pages, 15-second deadline) plus what it produces (a report of page signals and URL issues). The negative scoping ('No paid provider request or Lighthouse') separates it from the cost-incurring analysis tools in the sibling list.

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?

The 'No paid provider request or Lighthouse' clause implicitly tells the agent when not to pick this tool, which is useful. However, there is no explicit when-to-use statement and no routing to the obvious siblings (get_site_audit, list_site_audits) that complement a run/create tool, so the agent must infer the workflow.

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