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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, but the description goes well beyond them: it discloses the crawl source (homepage + sitemap + linked pages), robots.txt compliance, sampled (not full) coverage, no JavaScript execution, no rankings/traffic/backlinks, and the prioritised output shape. This is unusually rich behavioural disclosure.

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 purpose and differentiator, then usage, then behaviour and exclusions; each sentence carries information. It is long and the 'Do not use it for private or local addresses' clause slightly overlaps the earlier 'never guess page addresses', but no sentence is 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?

For a 3-parameter open-world crawl tool with an output schema, the description covers trigger conditions, crawl scope, limits, degradation behaviour, and explicit out-of-scope items. Nothing an agent needs to call it correctly is missing.

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 baseline is 3, but the description adds real meaning: max_pages default 10, judge is off by default and rate-limited per day with graceful degradation when unavailable. It reinforces rather than merely repeats the schema text.

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+resource+scope ('audit a whole site or several pages for SEO') and immediately adds the differentiator 'it finds the pages itself', which separates it from the sibling audit_page. An agent can route site-wide vs single-page audits without opening either 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 explicit when-to-use via realistic user utterances ('audit example.com', 'which pages are worst?') plus 'never guess page addresses for those', and states when-not ('private or local addresses', collecting content). It does not name audit_page as the alternative for single-page audits, so the routing is implied rather than explicit.

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