query_search_analytics

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is free. Beyond that the description discloses real behavioral nuance: sort_by is applied to the fetched rows while Google always returns top rows by clicks, data_state=all mirrors the UI, and grouping behavior differs by level. It does not discuss permissions or result size limits, but the added semantics are substantive.

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?

Purpose is front-loaded in two short sentences, then an argument list where nearly every line adds non-obvious semantics (spelling variants, sort vs. Google ordering, grouping). Dense, but little waste; the format is scannable rather than padded.

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 22-parameter tool with an output schema and rich annotations, the description supplies the parameter semantics and ordering caveats an agent needs. Remaining gaps (search_appearance filter, any limits on max_rows) are small relative to what is covered.

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 0% across 22 parameters, so the description carries the full documentation burden and mostly succeeds: it explains site_url formats, date-vs-days precedence, allowed dimension and search_type values, the multilingual/spelling-variant matching of query_filter, regex vs substring filters, ISO country codes, and the limit/max_rows split. Only search_appearance is undocumented as a filter, which is a minor omission against an otherwise thorough mapping.

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 concrete verb+resource (query Search Analytics rows) and positions itself as 'the general-purpose query tool', which implicitly contrasts with the many specialized siblings (top_terms, queries_for_page, striking_distance). It stops short of naming a sibling it is chosen over, so an agent must still infer the boundary.

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 general-purpose query tool' implies it is the fallback when no specialized sibling fits, which is usable guidance. But there is no explicit when-to-use/when-not statement and no named alternative, so the routing decision is left to inference.

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