generate_captions

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

Without annotations, the description carries the full burden. It discloses that caption timing uses whisper timestamps when available, otherwise proportional, and that shorts get karaoke word-highlight. However, it does not mention that the captions are burned into the video (destructive), any prerequisites beyond narration, or error conditions. More context on side effects would improve transparency.

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?

Three sentences: first defines purpose, second explains algorithm, third gives ordering hint. No redundant words. Front-loaded with the core action 'Build burned-in captions', making it efficient and scannable.

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 3 parameters and no output schema, the description provides key information: purpose, algorithm (timing method, karaoke), and execution order. It does not explain what 'burned-in' means or the effect on the project video, but the implication is reasonably clear. More details on prerequisites or output behavior would make it 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?

The schema covers 67% of parameters with descriptions (position and highlightColor). The description adds meaning beyond schema by explaining the timing algorithm and karaoke feature, which contextualizes the highlightColor parameter. It also clarifies that projectId refers to the project containing narration audio, providing semantics for the undocumented projectId parameter.

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 clearly states 'Build burned-in captions from the narration audio', specifying a specific verb and resource. It distinguishes from sibling tools by mentioning 'Run after generate_narration' and noting the karaoke word-highlight feature for shorts, which sets it apart from other tools like generate_narration or assemble_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?

The description provides clear usage context by stating 'Run after generate_narration', establishing a dependency and ordering. However, it does not explicitly list alternatives or when not to use the tool, though no direct alternatives exist among siblings. The guidance is strong but lacks explicit exclusions.

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