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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds useful context about micros money units and query shape, but says nothing about the account binding or result limits.

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?

Three sentences: intent first, example second, unit caveat last. No filler, and the most operationally important caveat (micros) is included.

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 general-purpose query tool with a thin two-param schema, the description gives enough for correct invocation: the query language, an example, and the money-unit gotcha. It could note row limits or the customer id source (which the schema already covers).

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?

The 'property' parameter is described in the schema as a customer id from list_properties, and the description supplies a full example GAQL query clarifying 'query' even though schema coverage is only 50%. Together they leave little ambiguity.

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+resource: runs a GAQL SELECT against a customer account, and gives a concrete example query. This clearly distinguishes it from the sibling analytical tools like ads_campaign_performance, which are fixed-purpose reports.

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?

Implies usage for arbitrary GAQL queries but gives no explicit when-to-use vs when to prefer the many purpose-built sibling tools such as ads_campaign_performance or ads_device_performance.

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