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

Beyond the readOnly/idempotent annotations, the description discloses critical behavioral details: queued:true means not started and no cost incurred, terminal statuses include a credits block, and it mandates reporting credits.net and balance. It also warns against quoting pre-flight estimates and attaching purchase suggestions, which are non-obvious side effects not covered by annotations.

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 long, but every sentence carries essential operational detail—polling cadence, failure handling, credit reporting, animation quality gate, and cost reporting rules. It is front-loaded with the core purpose, then progressively adds necessary nuance without redundancy. No filler exists.

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 an output schema, the description thoroughly covers all response-handling requirements: interpreting queued status, handling error enrichment, reporting credits, and checking animation quality gates. It leaves no ambiguity about what the agent should do with the tool's result.

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 sole parameter jobId is fully described in the schema as 'Job id.' The description adds context that write tools return this ID, but the parameter meaning itself is already clear from the schema. No additional semantic depth is needed for such a trivial parameter, so baseline 3 is appropriate.

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 states the tool polls a job and explicitly ties it to every write tool that returns a jobId. It differentiates itself from sibling tools like retry_job and cancel_job by focusing on status retrieval, giving a specific and unambiguous purpose.

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 provides explicit when-to-use guidance: poll after write operations, poll every few seconds, handle terminal states, and avoid retry when failureAction is edit_input. It also instructs when not to claim completion (animation quality gate) and how to handle credits reporting, covering both usage and non-usage scenarios.

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