Get audience insights

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

Annotations already mark the tool as read-only (readOnlyHint=true) and non-destructive (destructiveHint=false), so the description does not need to repeat that. It goes well beyond annotations by disclosing the server-side window clamping ('at most 60 days, always ending before today – a wider range is trimmed, not rejected'), the benchmark behavior (always returns the 25 accepted values, and adds a benchmark object when a category is set), and the capability requirement. These are significant behavioral details that an agent would not know otherwise, making the tool's runtime behavior fully transparent.

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 every sentence carries information. It is front-loaded with the core purpose, followed by return fields and specific behavioral notes. The structure is logical and avoids redundancy. It could be slightly more concise (e.g., the capability note could be trimmed), but it is not verbose or repetitive. The density of useful facts justifies a 4, as it is more than minimal but still efficient.

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?

Given that the tool has an output schema (so return value details are covered elsewhere), the description covers all critical aspects an agent needs: the purpose, the response structure (list of keys), the benchmark behavior, the clamping behavior, and the prerequisite capability. It even explains how to discover valid benchmark categories (omit the parameter). There are no missing pieces that would prevent a correct invocation or interpretation. The description is complete for its complexity.

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 100%, so the baseline for this dimension is 3. The description adds meaningful semantics beyond the schema: for benchmark_category it explains 'Must be one of the benchmark_categories the response lists; omit it on the first call to read them,' which is crucial usage guidance not present in the schema. It also clarifies endDate clamping and that platform values are constrained to an enum (though schema already lists that). The additional explanation of the interplay between benchmark_category and the response's benchmark_categories adds real value, so a 4 is warranted.

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 begins with a precise, specific statement of what the tool does: 'Who follows the profile, when they are online and what they tap on it.' It clearly identifies the resource (profile audience) and the action (retrieving insights). It also notes it's a single endpoint for every network selected via 'platform', which distinguishes it from generic analytics tools. The level of detail about return fields (audience.countries, activity_by_hour, etc.) leaves no ambiguity about the tool's purpose.

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 gives clear context on when to use the tool—when you need audience composition, activity patterns, or benchmark comparisons. It also provides a critical prerequisite: 'Requires the 'profile_analytics' capability on the profile's TikTok account,' which is a form of usage constraint. However, it does not explicitly name alternative tools or state 'use X instead when you need Y,' leaving some inference to the agent. It is still clear and actionable, so a 4 is appropriate.

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