poll_audience_operation

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

With no annotations provided, the description must carry the behavioral burden. It discloses that the tool makes exactly one call to get_audience_operation, does not loop internally, and exposes terminal states. This meaningfully helps an agent avoid hammering the API. It doesn't describe the return payload shape or error behavior, but the core non-obvious behavior 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?

Three sentences, each carrying distinct information: what it does, how to call it, and what it deliberately avoids. No filler or repetition, and the most important behavioral constraint (no internal loop) is prominently included.

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 simple polling helper, the description covers purpose, retry pattern, terminal states, and rate-limit rationale. The main gap is that it doesn't specify the structure of the returned 'current state' or explain how this differs from calling get_audience_operation directly. This is a minor omission given the tool's simplicity and the lack of an output schema.

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 input schema already describes operation_id and custom_audience_id, covering 67% of parameters. The description adds no new parameter-level meaning, and it does not help clarify the undocumented ad_account_id. Since the coverage is not high enough to fully rely on the schema, the gap around ad_account_id remains, but this is acceptable for a simple helper.

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 clearly identifies the tool as a helper to poll a custom audience mutation, stating it calls get_audience_operation once and returns the current state. This is a specific verb+resource pairing that distinguishes it from nearby mutation tools. However, the phrase 'poll ... until terminal' is slightly at odds with the explicit note that it does not loop internally, so the precise scope of a single call is a bit muddled.

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 gives explicit usage direction: call repeatedly with backoff and expect processing to transition to succeeded/failed. It also explicitly says the agent controls retry timing to respect rate limits, which tells the agent when and how to invoke the tool. This is actionable and complete.

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