Fix a video beat

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

Annotations provide minimal safety hints (all false), so the description carries the full burden. It discloses that the tool modifies the video track only, keeps audio byte-identical, bills only the replacement seconds (~1/3 of full render), and warns about lip-sync issues under dialogue. This is thorough behavioral disclosure beyond the schema.

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 a clear logical flow: core action, use cases, billing impact, and a critical warning. No fluff; every sentence serves a purpose and the most important constraint (video-only splice) is front-loaded.

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?

The tool is complex (6 params, nested array, specific constraints) and the description covers its purpose, constraints, and billing implications well. It misses the output format (e.g., returns a job ID or new video URL) and error conditions, but the core use cases are fully addressed.

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%, giving baseline 3, but the description adds context: the 1.5-8s window constraint, the meaning of prompt relative to master style, and the importance of speechWindows in avoiding dialogue overlap. This elevates understanding beyond bare parameter names.

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 precise verb-resource pair: 're-render ONE time window' of an existing video, and further distinguishes itself by specifying VIDEO TRACK ONLY with byte-identical preservation of the rest. It clearly separates from siblings like full re-render or clip_video by emphasizing surgical splicing.

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?

Explicitly states when to use ('when one beat/shot is broken'), when not to (avoid dialogue windows), and names the alternative (full re-render) with reasoning. Also gives a concrete negative condition and instructs to pass speechWindows to enforce that constraint.

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