Add or Remove Audience Members

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

With no annotations provided, the description carries full behavioral burden. It clearly communicates mutation ('Add or remove'), asynchronous execution ('Returns an asynchronous operation ID'), and audience scope ('existing custom audience'). It does not disclose rate limits, file size limits, required permissions, or whether identifiers are deleted from the audience on remove vs the whole audience being detached. The async disclosure is the main useful behavioral detail.

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 sentences: the first states the action and the two input modes; the second states the return type. Every word earns its place, and the most decision-relevant detail (whether this is a mutation and how it behaves) is front-loaded.

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?

The description covers the tool's purpose and async return signal, which are the essentials. However, with no output schema and no annotations, an agent cannot tell how long the operation takes, whether nested objects appear in the response, or what happens if both file_id and identifiers are provided. For a six-parameter mutation tool, it is sufficient but not rich enough to be fully self-contained.

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 schema already documents all six parameters, including enum values and the 10,000-item inline limit. The description adds the distinction between inline and file-based input and the async response, but it adds no meaning beyond what the schema gives for identifiers vs file_id. Baseline 3 is appropriate because the schema does the heavy lifting.

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 a specific verb ('Add or remove'), a specific resource ('customer identifiers from an existing custom audience'), and the two input modes ('inline identifiers or an uploaded file_id'). It matches the tool name and title cleanly and distinguishes it from audience creation or merging siblings.

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 implies the core use case by naming the operation and mentions 'Returns an asynchronous operation ID,' which signals that callers should poll a status endpoint. It does not explicitly say when to use this versus get_audience_operation_status or prepare_custom_audience_payload, and it does not state that file_id or identifiers is mutually exclusive. Usage context is adequate but not fully explicit.

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