Finish video

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

Annotations only say readOnly=false and destructive=false, so the description adds crucial behavioral detail: it is non-destructive because 'the original is untouched' and it 'Returns a NEW video.' It also discloses performance and cost characteristics (~30s, a couple of credits) and clarifies it uses no AI model, which meaningfully shapes agent expectations. No contradiction with annotations.

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 dense but well-organized: core purpose up front, then pill behavior, then grain behavior, then a clear non-destructive return guarantee. Almost every clause delivers actionable information—constraints, defaults, mode combinations, and cost—without fluff. It earns its length.

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 7-parameter tool with no output schema, the description covers inputs, conditional requirements, behavior, and return type well. It specifies the input is a served mp4 URL from a previous render/job, explains what a NEW video means, and documents the main mode interactions. It could be slightly more explicit about what happens to pill-related parameters when pills=false, but the schema and description together make this reasonably inferable.

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 100%, so the baseline is 3, but the description adds real semantic value beyond the schema: it explains the relationship between pills and grain, gives character limits in prose, states copy quality guidance ('concrete real benefits, never fabricated stats'), and clarifies that header is required when pills is on. This goes beyond simply repeating property names and descriptions.

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 action—post-process an EXISTING rendered video—and names the two concrete finishing modes: reviewer-style proof pills and film grain. The phrase 'no AI model' and 'existing rendered video' clearly distinguishes it from generation and broader editing siblings. This is a specific verb+resource definition, not a tautology.

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 gives clear when-to-use context: apply it to an already-rendered served mp4 to add social-proof pills and/or an anti-AI grain pass. It also explains mode combinations, such as setting pills=false for a grain-only pass. However, it does not explicitly name sibling tools like edit_video, clip_video, or upscale_video or state when to prefer them instead, so it stops short of full alternative routing.

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