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

With no annotations provided, the description carries the full burden. It discloses that data may be partial, that isCurrent may be false, and that coverage ranges should be reported. It explains the semantic meaning of the returned data, such as asOfDate and source dates. This is transparent about the data's nature, though it doesn't cover pagination or error behavior.

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 a single dense paragraph, not front-loaded with the most critical info (though it starts with the core purpose). It packs many details about data semantics and conditions, which is valuable but makes the text long and somewhat difficult to parse quickly. It could benefit from structured bullet points, but every sentence contributes meaning.

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?

Given the tool's complexity (6 params, no output schema, no annotations), the description thoroughly explains data freshness, coverage, and validity conditions, giving the agent a clear picture of what the response represents. It hints at response fields (isCurrent, asOfDate, GSC columns). However, it lacks any guidance on pagination or sorting via cursor and sortKey, and it doesn't describe the full response structure.

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?

The schema has descriptions only for pageSize and windowDays (50% coverage). The tool description adds no information about any parameter, including cursor, sortKey, category, and sortDirection, which are undocumented. With 50% coverage, the description should compensate but does not, leaving parameter semantics incomplete.

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 clearly states the tool retrieves unified page-level metrics (search, citation, referral, citability, guard-rail) from Audit rollups. This is specific and distinguishes it from other metric tools in the sibling list by focusing on page-level and Audit rollup origin, though it does not explicitly name a contrasting sibling.

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 provides detailed guidance on data freshness (D-3 Pacific source dates), coverage caveats (published Audit snapshot may lag), and when page GSC columns are valid (only when availability is measured or verified_zero). It instructs to report partial coverage and compare periods only when verified. This gives clear usage context, though it doesn't explicitly point to alternative tools.

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