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

Annotations cover the safety profile (readOnly, non-destructive, openWorld, non-idempotent), and the description adds the async/progressive behavior that annotations cannot: it returns an audit_id plus first progress, and each subsequent call scans the next few pages. The 25-page cap and sitemap-fallback source selection are useful extra context.

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-loads what it does, then the multi-call workflow, then the outputs. Dense but every sentence carries information; the final clause on suggest_internal_links is a minor add-on but ties the audit to a downstream tool.

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?

An output schema exists so return structure needn't be explained, yet the description still summarizes the finished audit contents (issues by code, broken pages, duplicate titles/descriptions, orphan pages). The workflow loop is fully specified; only the absence of exclusion criteria versus sibling audit tools leaves a small gap.

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 both parameters are already documented (url format, max_pages default 10 / max 25). The description adds source-resolution behavior tied to url (sitemap vs home page links) but no syntax or format detail beyond the schema, so baseline 3 applies.

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 ('Start an SEO audit of a whole site') with scope (up to 25 pages) and source resolution (sitemap or home page links). It clearly distinguishes itself from get_site_audit, which it names as the polling counterpart, and from the page-level siblings like scan_page.

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 workflow guidance: call this first, then call get_site_audit with the returned id until status is complete. It also notes the audit powers suggest_internal_links. It does not state when to prefer this over deep_audit or a single scan_page, so no explicit exclusions.

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