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

Beyond the readOnlyHint annotation, the description reveals that the tool is a polling endpoint, that completion returns signed URLs, that it is free with credits settling on completion, and gives per-model time estimates. This is meaningful behavioral context, though it doesn't cover edge cases like invalid task_id or URL expiry.

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 compact sentences front-load the core purpose, then add polling guidance, result contents, cost behavior, and timing expectations. No filler or redundancy.

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 poller with no output schema, the description covers purpose, polling cadence, return values on completion, and cost behavior. It omits failure response details, but the mention of 'completed/failed' gives the agent enough to infer status handling.

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?

With schema description coverage at 0%, the description compensates by defining task_id as the identifier returned from generate_video. It clarifies the parameter's origin and role, which is sufficient for a single required string 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 opens with 'Status of a video job by task_id (from generate_video)', which pairs a specific verb/resource and identifies the originating tool. It distinguishes itself from generic task/asset getters by naming the return of signed video_url and preview_url.

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 explicitly frames usage as a poller after generate_video and gives a concrete poll interval ('every ~15-30s') and stop condition ('until completed/failed'). It doesn't explicitly mention alternative tools like get_task or when not to use it, so it stops one point short.

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