Finish video

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

With annotations all set to false (readOnlyHint, destructiveHint, idempotentHint), the description carries the full behavioral burden and does so thoroughly. It discloses that the original is untouched (non-destructive), gives time and cost estimates (~30s, a couple of credits), explains the aesthetic effect of grain ('less AI'), and warns against fabricated stats. This is rich, specific behavioral context that goes far beyond what annotations provide.

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 single dense paragraph, but every sentence carries information: purpose, modes, constraints, and side effects. It front-loads the core action and the result (new video, original untouched). It could be slightly more streamlined, but there is no filler or repetition.

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 tool with 7 parameters and no output schema, the description covers the essential context: it explains both modes, how they interact, the return behavior ('Returns a NEW video'), and the non-destructive guarantee. It does not specify the exact output format (e.g., URL object), but for a post-processing tool that returns a video, that level of detail is likely sufficient. Minor gaps like error handling are not critical given the clarity elsewhere.

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?

The schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds value by explaining the visual and strategic purpose of pills and grain, clarifying that the agent authors the copy with character limits (repeated from schema but reinforced), and describing how grain works alone or with pills. This complements the schema without redundancy.

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 a specific verb ('Post-process') and a precise resource ('EXISTING rendered video (its served mp4 URL)'), immediately distinguishing this from generation or editing tools. It names the two modes (reviewer finish and grain pass) and the visual elements (header, sub-pill, proof pills), leaving no ambiguity about what the tool does.

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?

The description explicitly constrains when to use it: it requires an existing rendered video URL from a previous render/job, and states it is a post-processing step ('no AI model'). It does not explicitly name sibling alternatives like edit_video or upscale_video, but the strong precondition and the mention of 'proven direct-response reviewer finish' effectively distinguish it. The guidance is clear enough for an agent to route correctly.

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