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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces rather than contradicts them while adding substantial context annotations cannot carry: explicit failure handling ('Missing evidence and ambiguous page matches are explicit'), a clear statement of what is returned ('source material... not a new AI analysis'), and output guardrails about unverified claims and placeholders. This is unusually rich behavioral disclosure for a retrieval tool.

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 content is dense and mostly earns its place, but it is delivered as one long run-on paragraph with fragments ('Audit suggestions are not verified facts.') and the core purpose arrives well after the usage and formatting directives. Deliverable-formatting rules are blended with tool-selection guidance, which hurts scannability for an agent deciding whether to call it.

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 compensates by saying what is returned (the selected skill plus its relevant evidence) and what it is not (a new analysis). It covers audit resolution via audit_id/page/latest and the section default, leaving only the exact shape of the returned evidence unspecified.

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 100% and includes enum descriptions for 'skill' and 'section' plus resolution rules for page/latest/audit_id, so the schema does the heavy lifting. The description only loosely echoes that logic ('Finds an existing audit by page URL or client name') without adding format, precedence, or default detail beyond what is already documented.

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?

Mid-paragraph the description states a specific verb+resource: 'Finds an existing audit by page URL or client name and retrieves the selected skill plus its relevant evidence in one call,' and explicitly negates the misleading title by saying it is 'not a new AI analysis' and 'never starts an audit.' This lets an agent separate it from audit_page and the generation siblings, though the actual purpose is buried behind a long usage preamble.

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?

It opens with a clear trigger list ('Use when the user wants page fixes, message match, buyer objections, copy rewrites or a client test brief') and sets boundaries ('Read-only: never starts an audit, uses a page or publishes'). It stops short of naming sibling tools like audit_page or get_audit as the alternative path, so the routing is implied rather than explicit.

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