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

Annotations already declare write, destructive, non-idempotent behavior, but the description adds meaningful context beyond them: the operation is queued, and 'the script, voices and other clips stay' clarifies what is preserved. It still does not explicitly state that the target clip itself is replaced or how queue status is reported.

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?

The description is a compact paragraph with the operation type and purpose front-loaded in '[write, queued]' and the first clause. Dense but efficient; nearly every clause carries actionable information.

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 four undocumented optional parameters and no output schema, the description covers purpose, targeting, preservation, and one exclusion. It omits what the tool returns after queueing, how to track the job, and whether any parameter is effectively required despite all being optional in the schema.

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 0%, so the description carries the burden and largely succeeds: it explains `index` as the clip's params.ugc_clip on the timeline, `position` as the 1-based N-th made clip for older timelines, and that the target is found by `video_id` or `video_uuid`. It does not clarify whether the identifier parameters are alternatives, a required combination, or how conflicts are resolved.

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 a specific verb and resource: making one AI clip of a UGC video or film again, and scopes it with 'done or failed' and 'Not for promotion videos.' It distinguishes itself from promo-video siblings, though it does not explicitly name close siblings like retry_ugc_video or reset_ugc_video.

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 provides an exclusion ('Not for promotion videos') and explains the index-vs-position selection for older timelines, which is useful context. However, it never states when to choose this over retry_ugc_video or reset_ugc_video, leaving the main alternative-selection question to inference.

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