Pinterest audience insights

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

Beyond annotations (readOnlyHint=true, destructiveHint=false), the description adds crucial behavioral details: it is read-only and costs 0 credits, there is no date range (current snapshot only), affinity index is a comparison not a count, and size_is_upper_bound semantics. These significantly enrich the agent's understanding of output behavior and constraints.

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 relatively long but each sentence adds substantive value: scope, audience types, reporting guidance, date behavior, credits. It front-loads the core purpose and structures information logically. It could be trimmed slightly (e.g., the 'SAY THIS WHEN REPORTING' parenthetical), but it remains focused and efficiently packed.

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?

With no output schema, the description provides a strong conceptual outline of what will be returned (interest categories, demographics, affinity index, size flag) and explains key semantics. It does not enumerate exact fields or response structure, but for an agent deciding whether to call and how to interpret results, it is sufficiently complete for the tool's simple two-parameter interface.

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 description adds meaning to the insightType parameter by detailing the three enum values and their roles (baseline vs. comparative audiences), going beyond the schema's minimal description. It does not directly explain adAccountId, but the schema coverage is 50% and the description compensates for the key parameter. The affinity index explanation also clarifies potential interpretation of output fields.

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 clearly states the tool returns audience composition data (interest categories with affinity indices, demographics) rather than performance metrics, and explicitly names the three audience types including the baseline. It distinguishes itself from performance reports and sibling analytics tools like pinterest_analytics, so the purpose is unambiguous and specific.

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?

It states this is an input for creative briefs, not performance reports, providing clear context for when to use. It also gives explicit reporting instructions for affinity index and size upper bound. However, it does not explicitly name alternative tools or state when not to use it beyond the performance-report distinction, leaving some inference to the agent.

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