compose_final_video

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: voice selection fallback ('Voicebox voice-clone when available, else say'), the action of rendering narration and overlaying it, and the return of both the final mp4 and each beat's duration. It also hints at the need to account for durations in pacing. This goes beyond a simple restatement and provides practical behavioral context.

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 compact yet information-dense. It front-loads the 'ONE-CALL FINAL CUT' purpose, explains the process in one sentence, states return values, and adds a practical tip. No word is wasted; every sentence contributes actionable information.

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?

Given the tool's complexity (6 parameters, no output schema, no annotations), the description covers the essential usage: it explains what the tool does, what it returns, and how to avoid timing pitfalls via the tip. It does not detail error conditions or prerequisites beyond the schema, but the core context is sufficiently complete for an agent to invoke it correctly.

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 description coverage is 100%, so the baseline is 3. The description adds value by explaining how engine and voice parameters interact ('Voicebox voice-clone when available, else say') and mapping the core flow to the 'beats' and 'atSeconds' parameters. This clarifies the intended overall behavior beyond the schema's individual parameter 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 clearly defines the tool as a one-call operation that renders narration for each beat (using Voicebox when available, else say) and overlays it onto the recorded video at specified offsets. It explicitly names the return value (finished .mp4 and per-beat durations), which distinguishes it from sibling tools like render_narration and mux_narration.

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 tip provides clear workflow guidance: render beats first to learn durations, pace the recording to them, then use this tool to compose. This implies when to use the tool (after recording) and suggests a best practice, though it does not explicitly state when to prefer alternatives like render_narration or mux_narration over this combined tool.

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