Pinterest ads by audience segment

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Read-only, 0 credits' without contradiction. The description adds genuine behavioral context beyond the annotations: the 90-day lookback with max-90-day windows refused with reason, and unknown targeting types being refused BY NAME with per-level enum differences. This materially helps an agent predict failure modes.

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?

Every clause earns its place, covering the required param, scope semantics, date windows, and error behavior. However, it is long and written as dense rambling prose rather than terse structured guidance; the wordiness slightly hurts scannability for an agent parsing the description.

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 10-parameter tool with no output schema and very low schema coverage, the description covers the critical required parameter and key error/date semantics (refusals, lookback window, per-level enums). But it says nothing about the return shape, and the since/until/columns/granularity/id parameters remain undocumented. Given the tool's complexity, this is a solid but incomplete treatment.

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 only 20% (targetingTypes and scope carry descriptions), so the description must compensate. It does explain targetingTypes and scope meaningfully, but since/until/columns/granularity accept a 'default account' and the id lists are left semantically unaddressed. The description partially compensates for the coverage gap but stops short of documenting the remaining eight parameters.

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 the pointed question 'WHICH AUDIENCE SEGMENT actually delivered on Pinterest' and enumerates the breakdown dimensions (keyword, targeted interest, age bucket, gender, location, region, country, placement, app type, media type). This is a specific verb-resource-scope statement that clearly differentiates from generic siblings like pinterest_analytics by centering on audience segmentation via targetingTypes.

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 that targetingTypes is REQUIRED and explains why (it is the breakdown dimension). It gives precise scope semantics — account covers the whole account, while campaign/adGroup/ad each require their own id list — and flags that Pinterest ships no all-of-them form at those levels. It doesn't name an explicit sibling alternative to prefer instead, but the when/how conditions are concrete.

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