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

With no annotations, the description carries the burden well: it discloses the call is blocking, that videos are queued with a 60 s cap, and that a timeout returns queue status rather than a result, plus that images come back as URLs. It omits what credentials/permission model failures look like and does not tell the agent to poll check_job after a timeout.

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?

Two tightly packed sentences with the blocking behavior and the media-dependent return values front-loaded. Nothing is padding.

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?

Adequate for a 3-param, no-output-schema tool, but the input object is free-form (additionalProperties) and the description gives no hint beyond 'prompt, size, n, image, seconds'. It also leaves the post-timeout workflow (check_job/get_job_result) unstated, which is the main operational gap.

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%, so model, task, and the free-form input object are already documented in the schema. The description adds no parameter-level meaning (e.g., enum-like values for task, or what input keys apply per model), so the baseline 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?

States a specific verb and resource ('run a model') and adds the key qualifier 'synchronously', plus what comes back for each media type. It stops short of naming the async sibling it is contrasted with (submit_job), so the differentiation is implied rather than explicit.

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?

'Synchronously' hints at when this is preferred over the async path, but no alternative is named and no when-not-to guidance is given. An agent must infer from sibling names like submit_job/check_job that this is the blocking variant.

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