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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds two genuinely new traits: it is free to call (cost/billing behavior) and results are returned newest-first, neither of which is derivable from the annotations or schema.

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?

Three short sentences with zero filler: purpose first, then cost, then the motivating use case. Each sentence carries distinct information and nothing is repeated from the schema or annotations.

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 simple two-parameter list tool with no output schema, the description covers purpose, pagination, ordering, and cost. It does not hint at what an audit record contains beyond audit_id, which is a minor gap given no output schema exists to compensate.

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% (page and per_page are both documented with ranges), so the baseline is 3. The description adds the result ordering ('newest first'), which is not in the schema and materially affects how an agent interprets and navigates page numbers.

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 and resource ('List this account's past AI Visibility Audits') plus scope and ordering ('paginated, newest first'). The phrase 'instead of re-running an audit' implicitly distinguishes it from the run_brand_audit sibling and from get_brand_audit's single-record fetch.

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 a concrete use case: finding an earlier audit_id rather than re-running (and re-paying for) an audit. That is effectively a when-to-use condition pointing away from run_brand_audit, but there is no explicit when-not-to-use or direct sibling naming.

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