GAQL で Google 広告を検索

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description reinforces the read-only nature. It adds genuinely new behavioral context absent from annotations and schema: field names must be snake_case, returned keys are camelCase, and int64 values are returned as strings. No mention of pagination behavior or failure modes, keeping it out of the 5 band.

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-loads the verb and resource, then read-only status, then when-to-use, then the output-format quirks. Every clause carries information; no filler or repetition.

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 compensates by explaining return-key casing and int64-as-string behavior, which is exactly what an agent needs to consume results. Minor gaps remain around pagination/row-limit interaction and error handling, so not a full 5.

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% (baseline 3), and the description layers on query-authoring semantics the schema omits: a concrete example query plus the snake_case field-name convention that governs the required 'query' parameter. row_limit and customer_id are left to the schema, which already documents them.

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 (execute) plus resource (arbitrary GAQL via googleAds:searchStream) and immediately distinguishes it from the typed sibling tools by naming the query categories it uniquely unlocks (search terms, per-keyword performance, assets, region). An agent can tell it apart from google_ads_report/google_ads_keywords without opening any 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?

Explicitly scopes usage to data the typed tools cannot retrieve, which implicitly routes the agent here as a fallback and away from siblings. It stops short of naming a specific alternative tool or stating an exclusion/exhaustive condition, so it falls just below the top band.

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