Export scene

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

With no annotations, the description carries the full burden and does disclose real process behaviour: it downloads each clip, runs ffmpeg normalisation of size, fps and audio, joins them, and executes on the local machine. It does not cover auth/permission requirements, failure modes when a clip is missing, or expected runtime for large scenes.

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?

A single front-loaded sentence states the operation and output first, then the mechanism in a compact parenthetical. Every clause earns its place, including the return value.

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?

It fills the biggest gap by stating the return value ('Returns the path') despite no output schema, and clarifies the processing pipeline. However, with five parameters and only one documented, plus no statement of preconditions or failure behaviour, an agent still lacks enough to invoke it confidently in edge cases.

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 only 20% (just project_id), leaving width, height, out_dir and scene_id undocumented in both schema and description. The description's mention of 'MP4' and 'on this machine' faintly gestures at out_dir and dimensions but never maps them, so it does not compensate for the coverage gap.

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 names a specific verb ('Combine'), the resource ('a scene's clips') and the concrete output ('one MP4'), which naturally distinguishes it from sibling read/download tools like flow_download_media. It is a single-resource composite operation and reads clearly, though it does not explicitly name the siblings it is not.

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?

Usage is only implied: a scene must already exist with clips (via flow_create_scene / flow_add_clips_to_scene) before this makes sense, and the description never states that precondition or any exclusions. There is no explicit 'use this when...' routing against alternatives such as exporting individual media.

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