compose_video

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

The description adds extensive behavioral details beyond annotations: scenes are normalized, optional soundtrack replaces scene audio, voiceover ducks audio, and return value is a request_id to poll. No contradiction with annotations (readOnlyHint=false, destructiveHint=false).

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 paragraph that is dense but well-structured, front-loading the main action and then detailing parameters. It could be slightly more scannable with bullet points, but it is still concise for the complexity (9 parameters).

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 absence of an output schema, the description explains the return value and polling workflow. It covers typical use cases and most parameters. It doesn't cover error handling or edge cases, but for a tool with openWorldHint=true, it is reasonably 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?

With 89% schema coverage, the description still adds significant meaning: clarifies that scenes items can be request_id or video_url, duration_seconds trims/extend, normalize purpose, distinction between URL and request_id for audio/voiceover, and subtitles are burned-in. The schema already describes many parameters, but the description enriches understanding.

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 the action ('Stitch 2–20 finished video scenes into ONE final clip server-side'), the resource (video scenes), and the outcome. It distinguishes from siblings like generate_video (produces individual scenes) and wait_generation (polling). The typical flow is also mentioned.

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 explains when to use (after completing video generations, pass request_ids or media URLs) and provides a typical workflow. It lacks an explicit when-not, but the context is sufficient for an AI to understand the tool's place in the pipeline.

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