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

Annotations already declare write/destructive/non-idempotent, but the description adds substantive behavior beyond them: the job is queued, completed work is preserved ('what is done stays'), and the timeline is re-laid-out. That tells the agent exactly what gets destroyed versus reused, which the annotations cannot express. It does not cover cost, latency, or the return value of the queued job.

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?

A single dense sentence with the write/queued tag front-loaded, plus parenthetical examples and the exclusion placed after the main statement. No filler, though the compression ('ask a UGC video ... for its missing parts') costs a little immediate readability.

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 destructive, queued mutation with no output schema and zero parameter documentation, the description covers intent and preservation semantics but leaves the agent guessing about the async result (job id? polling?), whether both identifiers may be passed, and failure behavior. Adequate, not complete.

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 0% and the schema only supplies titles and types, so the description must compensate. It does clarify that the tool is looked up by either `video_id` or `video_uuid` (implying alternatives rather than both), but gives no format, precedence, or required-ness guidance for the two identifiers.

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 (retry) and resource (a UGC video/film) plus the exact object of the retry: missing parts such as failed AI clips or unmade voice lines. It also explicitly contrasts with the promo-video path, so the agent can separate it from regenerate/render siblings without opening a schema.

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 a clear when-to-use condition (failed AI clips, voice lines not made) and an explicit exclusion (promotion videos belong to 'regenerate'). The destination for the exclusion is named only loosely as 'regenerate' rather than the exact sibling id, and no prerequisite (e.g. that the video already exists) is stated, so it stops short of a perfect 5.

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