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

The description adds substantial behavioral detail beyond the readOnlyHint and destructiveHint annotations: it specifies JSON Lines output, a first-line schema marker, nested per-row objects, snake_case GAQL field names, enum values returned in Google format, and detailed error messages on API failure. This is especially valuable given the lack of an output schema, though it does not cover rate limits, timeouts, or authentication requirements.

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?

Two sentences carry the full payload: purpose first, then output format and error behavior. There is no filler, no repetition of schema text, and the most important scoping information is front-loaded.

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 tool with 8 parameters and no output schema, the description does a good job explaining what the caller receives (JSON Lines schema line plus rows, snake_case fields, enum values) and what happens on failure. Minor gaps remain, such as whether results are paginated or batched and what occurs with zero rows, but these are not critical given the schema's parameter documentation.

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?

Input schema coverage is 100%, so each parameter already has a meaningful description. The tool description adds no per-parameter semantics beyond confirming the query is structured GAQL and that output field names are snake_case; it does not elaborate on accountId meaning, date pairing rules, or predicate/orderBy syntax beyond what the schema provides. Baseline 3 is appropriate.

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 opens with a specific action and resource: 'Execute a structured Google Ads GAQL query for one account.' This clearly distinguishes it from sibling tools like google_ads_reports_list or google_ads_report_columns by naming the platform and execution verb, so an agent can select it without opening schemas.

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 context is implied: use this when you need to run a GAQL report query for a single Google Ads account. However, the description never explicitly states when to choose this over siblings, nor gives negative guidance such as 'not for listing available reports' or 'not for fetching column metadata.' The one-account scope is useful but not a full when-to-use/when-not-to-use statement.

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