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

The description adds valuable behavioral context beyond the annotations: it requires a connected Photo AI Studio account and warns that calling the tool can start the sign-in flow. This is non-obvious side-effect information that the readOnly/idempotent hints do not convey. There is no direct contradiction with the 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 compact and front-loaded: the first sentence states the core purpose and return value, and the second sentence adds only the essential auth caveat. There is no redundant or filler content.

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 read-only polling tool, the description covers what the operation is, how to identify it, what the tool returns, the account prerequisite, and the sign-in side effect. The lack of an output schema is adequately compensated by the explicit statement that it returns the state and result URL.

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 single parameter prediction_id is already fully documented in the input schema with the same provenance information ('returned when the operation started'). Since schema description coverage is 100%, the description does not add meaningful parameter-level detail beyond the baseline.

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 a specific action — checking an operation started by generate_photo, edit_image, or create_video — and the expected result (state and result URL). It is distinct from the sibling list_predictions by focusing on a single operation, though it does not explicitly name that sibling or draw the contrast.

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 identifies when to use the tool: after an asynchronous operation has been started and you need its state or finished result URL. It also notes the account requirement and sign-in flow, but it does not mention alternative tools such as list_predictions or state when not to use this tool.

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