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

Annotations already declare idempotentHint=true, destructiveHint=false, and openWorldHint=false; the description adds the multi-call polling contract and the state machine, which annotations cannot express. It does not explain the readOnlyHint=false signal, so a reader cannot tell whether repeated polling has any side effect. It also never says what check_again_in_seconds is or where it comes from.

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 opens with the triggering condition and then the return contract, before placing the call sequence and the final action in order. It is one long sentence, but each clause adds new information (states, file links, polling, sharing), with almost no repetition. It is dense but not padded.

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?

Output schema exists, so return values do not need detailed description, and annotations cover the safety profile. The description supplies the polling loop that neither structured field can express. Remaining gaps are failure handling on the 'failed'/'refunded' states and the meaning of the check_again_in_seconds field.

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 50%: 'id' is documented in the schema and reinforced by 'the returned id' in the description, but 'type' (enum image/video/voiceover) has no description text anywhere. The enum values are largely self-evident from the sibling create_* tools, so the description compensates for the id but not for the type parameter.

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 names a specific verb and resource ('returns the state of one creation'), enumerates the possible states (queued, processing, completed, failed, refunded), and says file links appear once completed. That clearly separates it from list_my_creations and the create_* siblings.

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 exactly when to call it ('when a creation was started and the user wants its result'), which prerequisite tool precedes it ('after create_* with the returned id'), and how to poll ('again after check_again_in_seconds while it is not finished'). The follow-up action (share the result link) is also spelled out, so no routing is left to inference.

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