What an audience is into

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavioral context beyond them, specifically that most metrics are licensed separately, that a 401 means missing entitlement rather than a bad key (do not retry), and that validation runs before authorization so a 422 is silent on entitlement. This directly shapes how an agent should react to errors.

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, front-loaded with the purpose before the licensing caveats, and every sentence carries operational value. The error-code detail is dense but justified for a tool where entitlement failures are common.

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 13-parameter tool with no output schema, the description covers purpose, the dimension-to-metric mapping, and the critical licensing/error behavior. It omits anything about return shape or pagination, but with no output schema and rich parameter documentation that gap is minor.

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 92%, so the schema already documents parameters, making a 3 the baseline. The description adds one conceptual relationship — dimension determines the valid metric/breakdown pair — but does not add format or syntax detail for the 13 parameters beyond what the schema provides.

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 states a specific measure and resource ('Affinity of one audience segment for personas, social ad channels, ad categories, advertisers, app categories or other apps'), which is far from a tautology and enumerates the affinity dimensions clearly. It does not name or contrast with the closest sibling (sensortower_audience_demographics), so an agent must infer the boundary itself.

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?

'Pick the dimension and this maps it to a valid metric/breakdown pair' gives some usage context, and the licensing guidance tells the agent what to do after a 401 ('pick another dimension'). However, there is no explicit when-to-use-this-vs-alternatives guidance and no statement of prerequisites before calling.

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