tiktok_get_audience_overlap

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

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose the read-only nature, establishing the absence of mutations—a meaningful safety signal. However, it does not explain parameter-driven behaviors such as overlapThreshold semantics, includeSavedAudiences impact, or the shape of returned diagnostics, leaving significant behavioral gaps.

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 a single, polished sentence with the key read-only qualifier front-loaded and entity types listed compactly. Every word earns its place, with no repetition or fluff.

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 6-parameter diagnostic tool with no annotations and no output schema, a one-sentence description is insufficient. It omits the meaning of overlapThreshold, default limits, the relationship between adgroupIds and campaignId filters, and expected output structure. Agents would need to rely on schema defaults and external knowledge to invoke this correctly, which is a significant completeness gap.

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 descriptions cover only adgroupIds, campaignId, and advertiserId; limit, overlapThreshold, and includeSavedAudiences lack schema documentation. The description adds meaning by naming the audience entities and targeting fields, but it does not clarify the numeric threshold, limit behavior, or the saved-audience inclusion flag. With 50% coverage, the description only partially compensates for what the schema leaves undocumented.

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 the tool's scope as 'read-only audience overlap diagnostics' and enumerates the entities it spans (ad groups, custom audiences, saved audiences, targeting fields), clearly distinguishing it from sibling tools like tiktok_get_audiences and tiktok_get_audience_details. It lacks a concrete action verb, but 'diagnostics' combined with the tool name implies retrieval or analysis. Not a tautology and genuinely informative.

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?

No when-to-use or when-not-to-use guidance is provided. The description does not name alternatives, exclusion criteria, or conditions that would make a different tool more appropriate. An agent must infer usage solely from the tool name and one phrase, which is minimal guidance.

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