Poll a job

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

Beyond the readOnly/idempotent annotations, it discloses two behaviors an agent could not infer: polling itself is free and the credit charge is applied once at completion, plus the retry cadence while a job runs. It does not describe the response shape for running versus finished versus failed jobs, and there is no output schema to fall back on.

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 short sentences, each earning its place: purpose first, then cost behavior, then retry instruction. Nothing redundant and no filler.

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 one-parameter polling tool with no output schema, the description covers when to call, what it costs, and what to do while pending. The remaining gap is what a successful result looks like and how a failed or expired job surfaces, which would matter for agent-side branching.

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 coverage is 100% for the single param, and the schema already explains that job_id comes from an accepted answer. The description reinforces this origin context but adds no new syntax, format, or constraint information, so the baseline applies.

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 and resource ("Fetch the result of a request that answered 'accepted'") and scopes it to long-running jobs such as AI transcription, which makes the intent unambiguous. It does not name a sibling alternative, but the trigger condition (an 'accepted' answer) is distinctive enough to separate it from the platform listing tools.

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 gives explicit entry conditions (only after a request returned 'accepted') and explicit retry guidance ("wait a few seconds and call again" if still running). No exclusion or named alternative is given, e.g. whether to use batch or get_transcript in some cases, which keeps it short of a 5.

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