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

Annotations already declare this as a safe, idempotent, closed-world read. The description adds substantial non-obvious behavior: it is free and charges no credits, makes no external call, derives entirely from crawl-time data, correctly warns that only BreadcrumbList's invalidCount is a per-type verdict and every other type is page-level, and documents the `notDerivable` section. This is far beyond what the annotations convey.

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 definition is long but front-loaded with the core purpose, then layered with caveats that each carry real weight (validity semantics, state handling, cost). It is dense rather than padded, though the cautionary sentences could be tightened slightly.

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-shape burden and does so: it describes typeGroups grouping, invalidCount, the `state` field with its values, and the `notDerivable` section. For a read-only report tool this is complete enough to call and interpret correctly.

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 `auditId` (optional, defaults to latest completed audit) and `projectId` (required) are already fully documented in the schema. The description adds no parameter-level detail beyond repeating the latest-vs-named-audit default, so the 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 — a structured-data report grouped by schema.org @type for a project's latest completed crawl — and immediately contrasts it against cousins by naming the report's scope ('PRESENCE AND PARSE VALIDITY, NOT A RICH-RESULTS ELIGIBILITY CHECK'). An agent can distinguish it from other get_audit_* siblings without opening the schema.

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 concrete usage instructions ('ALWAYS narrow on `state` first') and explains what the `no_audit` and `analysed` states imply, including the critical note that `typeGroups: []` is a real finding, not withheld data. It does not explicitly route the agent away from sibling reports like get_audit_comparison, so it stops short of a full when-not rubric.

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