edit_video

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

Annotations only declare non-read-only, non-destructive, open-world. The description adds substantial behavior beyond that: 300-clip/180-second caps, transition clamping to adjacent limits, v1-only caption/pause detection even when muted, ripple behavior when removing pauses, an explicit error on conflicting v1 transitions, and no automatic sync/drift correction. It also discloses the free/Pro gating, no-upload and no-history behavior, and default 1080p/720p handling.

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?

Nearly every sentence carries unique constraints, but they are packed into a single unbroken wall of text mixing purpose, limits, quota, captions and an embedded example. Front-loading is decent (core create behavior first) but the density hurts scanability and the login/Pro caveat arrives late.

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 very complex 8-parameter nested tool with no output schema, it covers limits, track semantics, transition behavior, captions, quota and the async job_id/polling contract, which is what an agent needs to invoke it correctly. Minor gaps remain on output_path/aspect/quality defaults but the return-value contract (job_id, poll job_status) is stated.

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 schema description coverage reported at 0%, the description carries the load and does so for the highest-risk fields: track/start rules per version, crop as source-edge percentages, place modes including custom normalized box, omitted defaults, pan/zoom ranges, and the tricky 'after_clip indexes the request array and must target v1' semantics. Several scalars (volume, fades, slow_zoom, mute, quality, output_path, remove_silences sensitivity) are left to the schema, so it is strong but not exhaustive.

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 opens with a concrete verb+resource+scope: 'Create a local video with sequential v1 clips and nonoverlapping v2 clips above them.' That clearly distinguishes compositing work from the sibling overlay tools (configure_overlay, render_overlay, add_overlay_to_video), though it never names them. It is dense but specific.

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?

It gives partial routing and conditions: returns job_id so 'poll job_status', overlays must come from configure_overlay, and free-vs-Pro limits are stated. However, it never explicitly tells the agent when to choose edit_video versus add_overlay_to_video or render_overlay, so the alternative-selection guidance is only implied.

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