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

Annotations supply the read-only, open-world, non-destructive profile, so the description's added details on pagination (cursor/nextCursor) and the enumerated crawl states (fetched, blocked, inconclusive, failed, pending) genuinely extend transparency. It still does not say what is returned for non-fetched URLs or how unfinished audits behave.

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 dense sentences with the resource and scope front-loaded, followed by the returned fields, then paging. No filler or restatement of the title.

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 carries the return-value burden and does a reasonable job: it names crawl state for every URL and the field set for fetched URLs. It is slightly incomplete in not describing output for non-fetched URLs or behavior when the audit is not finished.

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 75%, so the schema already documents runId, cursor and projectId well. The description only reinforces cursor/nextCursor paging semantics and adds nothing about limit, runId or projectId beyond what the schema says, which matches the baseline for well-covered schemas.

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 verb and resource ('Lists the URLs a finished SEO Audit discovered') and enumerates the per-URL data, which lets an agent separate it from list_audits/get_audit. It never explicitly contrasts itself with sibling listers like list_audit_findings, list_audit_links or list_audit_rows, so it stops short of full differentiation.

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 phrase 'a finished SEO Audit' implies the prerequisite that the audit must be complete, and 'Page with cursor and nextCursor' implies when to paginate, so usage is inferable. There is no explicit when-to-use/when-not-to-use guidance or statement about what to do if the audit is still running, so guidance is implied rather than stated.

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