Crawl the site and audit every page

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds operational details beyond annotations: respects robots.txt for Googlebot, same-host constraint, breadth-first strategy, and a time estimate. It does not contradict annotations and provides useful context on how the crawl behaves.

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 moderately long but each sentence adds value. It front-loads the core purpose, then lists the detailed outputs and ends with a practical usage hint. It avoids fluff and is well-structured, though slightly verbose in the output enumeration.

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 crawl tool with no output schema, the description covers the key aspects: what it returns (list of metrics), how to bound it, performance expectations, and constraints (same host, robots.txt). It does not mention authentication requirements or exact response format, but these are minor given the comprehensive summary provided.

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 50%, so the description should compensate. It does explain maxPages (bounding) and startUrl (implicitly), but concurrency is left unexplained. The description adds a performance note tied to maxPages but does not fully elaborate on all parameters. This is adequate but not exhaustive.

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 a specific verb ('crawl') and resource ('from a start URL'), and clarifies it audits each HTML page like page_audit. It lists the detailed site-level summary outputs, making its purpose unambiguous and distinguishing it from single-page tools like page_audit or specific checks like robots_check.

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 it (site-wide audit vs. single page via 'like page_audit') and gives practical guidance on bounding with maxPages and performance expectations. However, it does not explicitly mention alternatives or when not to use it, such as when a sitemap check or robots check would be more appropriate.

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