google ads run gaql

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

Annotations already carry readOnlyHint=true, idempotentHint, and destructiveHint=false, so the description need not restate them. It adds 'full flexibility' and a read-only SELECT example, but adds no new behavioral context such as result limits, pagination, or the need to validate queries first. This is minimal-but-adequate disclosure on top of strong annotations.

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 short and front-loaded with the core verb and resource, with an illustrative example that earns its place. 'Full flexibility for any reporting need' is a slightly promotional phrase but does not add significant noise.

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 two-parameter, read-only tool with a rich input schema and an output schema, the description covers what an agent needs to call it and what it returns. It could additionally mention the sibling validation tool, but the example and schema already make invocation unambiguous.

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 100%, so query and customerId are already defined, including the no-dashes format and query shape. The description's example adds a concrete illustration of valid GAQL but no additional parameter semantics beyond the schema.

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 action and resource: execute a raw GAQL query. The word 'raw' and 'Full flexibility for any reporting need' clearly set it apart from the many pre-built google_ads_get_* siblings. The SELECT example makes the exact operation concrete.

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 tells the agent when to use it: whenever flexible GAQL reporting is needed, implying it is the fallback for cases not covered by specialized getters. It does not explicitly name alternatives like google_ads_validate_query for validation or caution against using it when a targeted tool exists, so it stops short of a full when-not boundary.

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