create_custom_audience

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the most important behavior: processing is async and the caller must poll until the audience is published. It also states the return value (custom_audience_id). It doesn't mention failure modes or authorization requirements, but the async caveat is well covered.

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?

Two concise sentences with no filler. The core purpose, input mode, async behavior, polling instruction, and return value are all front-loaded. Every sentence earns its place.

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 9-parameter mutation tool with no annotations and no output schema, it covers the essential operational facts: how the audience is sourced, that processing is async, what to poll, and what is returned. The phrase 'if enabled' is somewhat ambiguous and ad_account_id is not explained, but an agent has enough to invoke the tool and monitor the operation.

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 78%, and the schema already documents file_id, name, filename, file_size, identifier_type, and identifier_resolution. The description reinforces the file_id-vs-empty choice but adds little beyond what the schema property descriptions already say. ad_account_id remains undocumented in both the description and schema, so some parameter semantics are still thin.

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?

States a specific verb ('Create') and resource ('custom audience'), and specifies the two source modes: an uploaded file via file_id or an empty/small audience if enabled. This clearly distinguishes it from sibling list/get/archive/merge/audience-member tools without requiring schema inspection.

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?

Explicitly tells the agent to poll get_custom_audience until published, which establishes the correct follow-up workflow. It also indicates when file_id should be provided versus the empty-audience path. It doesn't explicitly rule out alternatives like merge_custom_audiences or add_audience_members, but the core create-and-poll guidance is clear.

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