run_gaql

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

With no annotations, the description carries the full burden. It explicitly discloses that the tool is read-only ('cannot modify any Google Ads data') and that GAQL only supports SELECT, which is key behavioral context. It also provides a concrete query example. It does not mention pagination, rate limits, or error handling, but since an output schema exists and the tool is a raw query runner, these are less critical. The transparency is high, though not exhaustive.

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 concise, front-loaded with the purpose and usage guidance, and organized with an Args section that cleanly lists parameters. Every sentence earns its place: the intro defines the tool, the second sentence gives usage context, and the args section covers both parameters. No redundancy or fluff.

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 raw query tool with only two parameters, a clear read-only guarantee, and an existing output schema, the description is complete. It gives the exact fallback use case ('not covered by other tools'), parameter formats, and a query example. The presence of an output schema obviates the need to describe return values. Nothing essential is missing for correct invocation.

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%, so the description must explain both parameters. It does so effectively: customer_id is described as 'Google Ads customer ID (10 digits, dashes optional)' and query as 'A GAQL SELECT query' with a representative example. This adds substantial meaning beyond the bare schema properties (which have no descriptions), fully compensating for the coverage gap.

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 'runs a raw read-only GAQL SELECT query against the Google Ads API', naming a specific verb (run), resource (GAQL query), and its read-only nature. It explicitly differentiates from siblings by stating it is for reporting needs 'not covered by the other tools', making its purpose unambiguous and distinct from the other reporting tools.

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 explicitly states when to use this tool: 'for reporting needs not covered by the other tools', and clarifies that GAQL only supports SELECT, so it cannot modify data. This gives clear usage context and implicitly tells the agent to prefer sibling reporting tools when they fit, reserving this for raw queries. No exclusions are needed beyond that.

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