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

Annotations already cover read-only/idempotent, and the description layers substantial extra behavior: URL signing expiry of seven days, queue-reason semantics (plan_limit with position, render_capacity with estimated_wait_seconds), null handling for poster_seconds on older videos, and the meaning of AI_VIDEO_UNAVAILABLE. This is exactly the kind of context annotations cannot carry.

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?

Front-loaded with the return payload and the status enumeration, then progressively details poster variants and error codes. It is long but nearly every sentence carries information an agent needs; only the poster-type breakdown is slightly verbose.

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 no output schema, the description carries the burden of explaining returns and does so thoroughly, covering the success shape, the pending shape, and the failure shape. Minor gaps remain around how long status data persists and whether fields are absent versus null while processing.

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?

There is a single required parameter with 100% schema description coverage, so the schema already documents it. The description adds no format, source, or lookup guidance for video_id, leaving it at the baseline for full coverage.

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 exactly what the tool returns for a single video: status, progress, credits, and, when completed, download links. It's clearly a per-video status/result fetch, distinguishable from list-oriented siblings, though it never names show_video, wait_for_video, or list_videos to confirm the distinction.

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?

Usage is implied (poll this to learn whether a video is queued, processing, completed, failed, or cancelled) and the failure text hints at retrying later. But there is no explicit guidance on when to use this versus wait_for_video, show_video, or retry_video, and no stated conditions or exclusions.

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