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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses that unregistered and ephemeral one-shot audits are omitted, that last_report_run_id points to the latest completed report whose report was not deleted, and that the response includes total/has_more for pagination. This adds meaningful behavioral context without contradicting any annotation.

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 dense and front-loaded, with the main purpose in the first sentence. It is longer than average but every clause adds operational detail (ID relationships, exclusions, pagination, filter semantics). A slight trim could improve readability, but no sentence is wasted.

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 list tool with no output schema, the description covers return fields, pagination, filtering semantics, exclusions, and cross-tool ID usage. It anticipates likely follow-up actions (get_report, list_audits, list_issues) and provides enough context to invoke the tool correctly and interpret results. This is exceptionally complete.

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?

While the schema already covers all three parameters with descriptions, the description enriches the meaning of 'kind' by explaining that unclassified sites count as 'owned' and that 'prospect' only returns explicitly marked sites. It also clarifies pagination semantics (default limit, offset behavior) and the difference between last_run_id and last_report_run_id, adding real value beyond the schema.

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 opens with a specific verb ('List') and resource ('websites the organization has audited'), and immediately defines the contained fields (latest run status, health score, kind). It distinguishes itself from sibling tools by naming how its IDs relate to get_report, list_audits, list_issues, and by clarifying that unregistered/unused websites are excluded.

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 gives explicit usage direction: pass last_report_run_id to get_report, use website_id with list_issues/get_issue, and use list_audits for full history. It also states when to use kind=prospect for bulk deletion and that run_audit/add_website are for new registrations, effectively defining when this tool is and isn't appropriate.

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