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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered. The description adds genuine behavioral context that annotations cannot — notably that 'low_score' returns worst-first ordering and that 'errors' means HTTP errors. It says nothing about default ordering, how 'limit' affects result completeness, or whether truncation occurs.

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 short sentences with zero filler, and the core purpose is front-loaded before the filter list. The filter enumeration reads as a terse fragment, but that style suits a quick-scanning agent and wastes no tokens.

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 should say more about what each returned entry contains (URL plus what audit fields?) and about paging past the 200-URL cap. It covers the purpose and filter vocabulary adequately but leaves return shape and result exhaustion underspecified for a list tool.

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 only 33% (only 'site' carries a description), so the description must compensate. It does clarify all four 'filter' values with parenthetical semantics, but 'limit' is left entirely to the schema (default 50, max 200) with no hint about pagination or how to retrieve more than 200 URLs.

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?

Names a specific resource — sitemap URLs of a site together with their audit result — which clearly separates it from get_url_audit (single URL) and list_sites (sites rather than URLs). The verb is only implied by the title 'List audited URLs' rather than stated in the description, but the scope is unambiguous.

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 filter enumeration gives implicit guidance: pick 'missing_md' to find pages lacking Markdown, 'errors' for broken pages, 'low_score' to review worst performers first. There is no explicit statement of when to prefer this over get_url_audit for a single URL, and no mention that 'site' can be omitted for single-site accounts (that only appears in the schema).

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