remove_audience_members

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

No annotations are provided, so the description carries the burden. It discloses important behavioral requirements: idempotency, expected revision, and asynchronous polling. It does not cover irreversibility, authentication requirements, failure modes, or return behavior.

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 compact sentences with no filler. The core operation, required parameters, and follow-up polling instruction are all front-loaded and easy to scan.

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 mutating, asynchronous operation with no output schema or annotations, the description covers the essential call pattern but leaves gaps: the relationship between file_id and identifiers, ad_account_id context, operation result format, and error handling are not addressed.

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 by explaining the 'file or inline' distinction, hinting at file_id vs identifiers, and calling out required idempotency_key and expected_revision. However, schema coverage is only 38%, and key parameters like ad_account_id, identifier_type, and identifier_resolution remain unexplained.

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 uses a specific verb ('Remove') with a clear resource ('custom audience') and notes the two modes ('file or inline'). This clearly distinguishes the tool from sibling operations like add_audience_members and replace_audience_members.

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 when to use the tool (removing identifiers from a custom audience) and gives required usage context: Idempotency-Key, expected_revision, and polling via get_audience_operation. However, it does not explicitly mention when not to use it or name alternatives.

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