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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real behavioral detail beyond them: the comparison rows expose prevClicks/prevImpressions/prevCtr/prevPosition and change fields, and keys present in only one period are zero-filled. That zero-fill rule is exactly the kind of non-obvious output behavior an agent cannot infer from 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?

Front-loaded with the purpose and use case, then structured as row-shape, sort semantics, and a noise caveat — each sentence carries information. It is dense rather than padded; the bilingual Portuguese restatement is duplication but is a consistent convention across this tool family.

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 14 parameters, no output schema, and read-only annotations, the description carries the return-shape burden and does it: it enumerates the per-row fields including comparison and change fields, plus the zero-fill rule and sort tie-breaking. Combined with the schema's date/default documentation, an agent has everything needed to call and interpret this tool.

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%, so baseline is 3, but the description genuinely enriches the sort enum by explaining each mode ('position (lowest first)', 'growth (largest click gain vs comparison first)', 'decline (largest loss first)') and ties minImpressions to ctr/position analysis, which the schema only states as a generic filter.

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?

Opens with a specific verb+resource+scope: pages (URLs) of one property over a period, aggregated and sorted. It implicitly separates itself from query-level siblings by naming the resource as pages and adding 'Use for best/worst pages and pages that gained or lost clicks', but it never explicitly contrasts with get_page_performance or breakdown_by_path, both of which look adjacent.

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 use cases ('best/worst pages', 'pages that gained or lost clicks') and a practical operating rule: use minImpressions >= 20 for ctr/position to avoid noise. It does not state when NOT to use this tool or point to a specific alternative tool, so there is no exclusion guidance.

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