add_audience_members

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

With no annotations, the description carries the full behavioral burden. It discloses that this is an asynchronous operation requiring polling, that an idempotency key is required for safe retries, that expected_revision is needed for concurrency control, and that inline size is capped around 10k. It does not mention duplicate handling, response shape, or whether the operation is reversible, but the disclosed behaviors are highly relevant.

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 three dense sentences with no filler. It front-loads the core action, then critical requirements, then sizing guidance. Every sentence contributes useful information.

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 the lack of annotations and no output schema, the description covers the most important operational facts: prerequisites, async polling, and inline size limits. It does not explain return values or the undefined optional parameters, but the combination of schema and description is largely sufficient for correct invocation.

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 beyond the schema by explaining the file-or-inline choice and the ~10k inline threshold. However, schema coverage is only 63%, and parameters such as ad_account_id, identifier_type, and identifier_resolution are not clarified by the description. The description helps but does not fully compensate for the coverage gap.

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 and resource: 'Add identifiers to an existing custom audience.' It also distinguishes file-based from inline-based additions, and the sibling list includes remove/replace/merge operations, so the tool's role is clear.

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 explicitly states when to use the file approach vs inline identifiers ('Supports up to ~10k inline identifiers; use file for larger'), calls out required prerequisites (Idempotency-Key and expected_revision), and instructs the agent to poll get_audience_operation. This is strong routing and execution guidance.

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