Crawl and audit multiple pages

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

The description adds significant behavioral context beyond the readOnlyHint and openWorldHint annotations: it discloses a polite delay, that each page is fetched once and shared across checks, the '>50% of pages' heuristic for site-wide issues, and fallback to internal links. It does not mention baseline updates for compare_to_baseline (a side effect), but that is covered in the schema, and the description does not contradict 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?

The description is a single, dense paragraph that front-loads the action ('Crawl a site...') and uses a colon-separated list for the aggregates. It is efficient and every clause contributes value, though the length makes it slightly less scannable than a shorter alternative.

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?

For a tool with five parameters and a complex crawl-and-audit workflow, the description covers the core behaviors: crawl seeding, delay, page-sharing, and the specific aggregate checks. It does not enumerate the return structure in detail, but the output schema explains format options, and the description provides enough for an agent to understand the tool's scope.

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 100%, so the schema fully documents all five parameters. The description adds conceptual meaning by explaining the crawl context ('sitemap-index aware', 'falls back to following internal links') and the role of max_pages ('audit up to max_pages pages with a polite delay'), which goes beyond the schema's field-level descriptions.

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?

The description clearly states the tool's function: 'Crawl a site... and audit up to max_pages pages' and lists specific aggregated checks such as broken internal links, redirect chains, duplicate titles, and orphan sitemap URLs. This concrete enumeration distinguishes it from sibling tools like check_sitemap or seo_full_audit.

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 description implies when to use this tool by describing the crawl strategy (seeded from sitemap.xml, falls back to internal links) and the aggregation of site-wide issues across pages. However, it does not explicitly state when this tool should be preferred over alternatives like seo_full_audit or check_url_structure, nor does it mention exclusions.

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