Turn a clip into a finished UGC video

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the mutation/safety profile is covered structurally. The description still adds real context beyond them: cost is free at time of writing (live value from get_credits 'merge' key), rendering happens in the background, and the returned id lives in a different id space than the clip id. It does not, however, describe failure modes or partial-state behavior beyond the 'failed' status token.

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 core action is front-loaded in sentence one, followed by prerequisite, cost, return value, and the polling workflow. Every sentence is operationally actionable — there is no restatement of the name or filler.

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?

Despite no output schema, the description names the return field (merged_video_id) and how to consume it, and it closes the loop through get_video polling to download_video. For a 4-param async render tool, an agent has everything needed to call it and handle the result.

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 already 100%, so baseline is 3, but the description adds meaning the schema cannot: the `video` param is a clip id that must be in 'completed' status, and the returned merged_video_id is a distinct id space — a distinction an agent could easily get wrong. Music is confirmed optional while hook and app_video are effectively mandatory inputs.

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 concrete verb (put/merge) plus the exact inputs (app screen recording, hook overlay, optional music) and the output artifact (finished UGC video). The CLI equivalence line (`clipugc videos merge <clipId>`) and the 'completed' clip prerequisite make it unmistakable how this differs from create_clip or create_motion_clip.

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 the precondition explicitly (clip must have status 'completed', verified via get_video), the required ordering (files uploaded first), and the exact follow-up loop: poll get_video with kind 'finished' every 5-10s, then call download_video. Nothing about when to invoke this versus siblings is left to inference.

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