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

Annotations already cover read-only, idempotent and non-destructive, so the bar is lower, yet the description still adds meaningful behavior: server-side waiting that returns as soon as the render settles, and the fact that download URLs are short-lived. It does not mention what a failed or expired generation looks like or any rate limits.

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, front-loaded with what the tool is, then the waiting strategy, then the return nuance. Every sentence carries information an agent needs; nothing is 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?

With an output schema present, return values need not be spelled out, and the ephemeral-URL caveat covers the one thing the schema likely won't convey. The remaining gap is failure handling — what to do if the generation never settles or errors out.

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% and the schema already explains wait_seconds ('0 checks instantly', max 50), so the baseline is 3. The description goes beyond it by recommending 45 as the practical value and explaining the payoff in terms of expected call counts, which is genuine added meaning.

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?

States a specific resource and scope: 'Status of a generation_id from any create_* tool.' This clearly ties it to the create_* siblings as the follow-up call and implicitly separates it from download_artifact by noting completed results carry a download URL. It falls short of 5 only because it never names the sibling an agent might confuse it with.

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?

Gives real operational guidance: set wait_seconds (recommended 45) and one or two calls usually cover an image while a few cover an animation. That tells the agent how to poll in practice. It does not state when to stop checking or when to reach for download_artifact instead.

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