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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful behavioral context: URLs are returned once processing is finished, and the agent should display the finished image to the user. It does not explain polling cadence or what a not-yet-finished response looks like.

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 two sentences with no wasted words. It front-loads the tool's action and then adds a relevant user-facing instruction, making it easy to scan.

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 single-parameter, read-only polling tool with complete schema coverage and annotations, the description covers the essential context: what it checks, what it returns, and how to present the result. It could be stronger by clarifying polling behavior when images are not yet finished.

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 description coverage is 100%, and batchId is already documented as the value returned by create_image. The description reinforces that origin but adds no format, validation, or syntax details beyond the schema, so the baseline of 3 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 action and resource: checking images started by create_image and retrieving their URLs once finished. It clearly ties the tool to create_image, but does not distinguish it from sibling status tools such as get_generation_status or get_task_status.

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 clear usage context by linking the call to images started via create_image, and adds presentation guidance to show the finished image rather than only describing it. It does not state when to avoid this tool or name alternative status-checking tools.

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