Google Ads query (GAQL)

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so "read-only" in the description is redundant. The description does add real domain context beyond the annotations: GAQL syntax samples and the cost_micros/1,000,000 currency conversion. It omits pagination, the 500-row default, and any rate-limit or auth/account-linking caveats beyond the Search Console note.

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 sentence is front-loaded, followed by self-contained examples and a conversion footnote. It is somewhat long because three full SELECT statements are inlined, but each illustrates a distinct capability rather than padding.

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?

There is no output schema, so the description carries the burden of explaining return values, which it never does (no mention of row shape, field naming, or truncation at limit). Examples hint at the output columns, but an agent does not know what the response envelope looks like for this query 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 67%. The query param is only labeled "GAQL SELECT statement" in the schema, but the examples meaningfully teach the GAQL resource/metric syntax the agent must supply, adding value. The limit param has no description anywhere, and customerId's default behavior is only covered by the schema, so compensation is partial.

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 and resource ("Runs a read-only Google Ads Query Language query") that an agent can act on immediately. It's clearly distinct from the listing helpers (ads_list_accounts, ads_keyword_ideas), but it never explicitly says how it differs from ads_keyword_ideas/ads_keyword_volume, which overlap in output.

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?

Usage is implied through three concrete example queries (paid vs organic, search terms, campaigns), which telegraph when the tool applies. However there is no explicit when-to-use statement, no exclusion, and no guidance on preferring this over the sibling ads_* tools for keyword data.

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