Edit a video clip

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

Annotations are all false (readOnlyHint, destructiveHint, etc.), so the description carries the full burden. It clearly discloses key behaviors: the edit preserves original motion/timing, it is a paid render, and it returns a served URL. It also explains how the elements parameter affects behavior (restores real identity/product vs. plain restyle). No contradiction with annotations.

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 dense yet every sentence earns its place: purpose is front-loaded, followed by concrete use cases, the recommended clip length, a clear 'NOT for' section naming five alternatives, and a final note on cost and output. The structure guides an agent from selection to invocation without redundancy.

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 (video editing, multiple parameters, no output schema), the description covers purpose, usage, exclusions, cost, output URL, and best practices. It doesn't mention error scenarios or hard maximum video length, but the 'Best on 3–10s clips' is a reasonable heuristic. The schema covers source URL provenance. Overall, an agent has everything needed to decide and call the tool 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 coverage is 100% (all parameters have descriptions), so baseline is 3. The description adds meaningful context for the 'elements' parameter, explaining its purpose (identity/product grounding), the max count (≤4), and when to omit it (plain restyle). It also clarifies the 'instruction' parameter as 'in the user’s own words'. This goes beyond the schema's literal descriptions and aids correct usage.

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 specific verb ('EDIT/transform') and resource ('an existing video clip') and immediately defines the scope: keeps motion/timing, changes subject/setting/style. It provides concrete examples ('change the background to a city', 'restyle it as claymation'). It also distinguishes itself from five named sibling tools, so an agent can reliably tell edit_video apart from post_edit, generate_video, render_ad, dub_video, and recast_motion.

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 explicitly states when to use (for style/subject/setting changes) and when NOT to use, listing specific alternatives for each excluded case (mechanical cuts → post_edit, new video → generate_video/render_ad, translation → dub_video, face swap → recast_motion). It also adds a practical recommendation ('Best on 3–10s clips') and flags the paid nature. This leaves no ambiguity about tool selection.

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