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

Annotations already declare non-readOnly, non-destructive, idempotent, and closed-world behavior. The description adds substantial context beyond that: overlap moves later clips earlier, handles moves nothing, other_tracks stay can create timing drift and warnings, extract keeps tracks in sync, and changed/return behavior is described. This is rich behavioral disclosure for a mutation tool.

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 but front-loaded, starting with the core operation and then moving into mode and audio behavior. Most sentences earn their place by clarifying non-obvious effects. There is some repetition of schema-provided enum and URI details, which keeps it from being maximally concise.

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 complex timeline-editing tool, the description covers purpose, mode effects, linked-audio behavior, changed-output semantics, and a pointer to the server instructions for the edit result. An output schema exists, and the input schema covers most parameters, so the remaining gaps are minor. The main missing element is explicit sibling-tool routing.

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 high at 86%, so the schema already documents most parameters. The description still adds cross-parameter meaning, especially that kind crossfade is sound-only on video clips and requires mode handles for a visual transition. It does not cover every parameter in prose, but the added interaction guidance goes beyond the schema.

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 uses a specific verb and resource: it adds a transition at the cut after a clip and into the touching clip. It also explains linked-audio behavior, making the operation clear. It does not explicitly distinguish itself from sibling tools such as transition.set or transition.remove.

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 gives useful internal guidance for choosing kind crossfade versus mode handles, and explains overlap versus handles. However, it does not say when to use transition.add instead of transition.set, transition.remove, or audio.fade. Usage is implied by the cut/clip context rather than explicitly routed against alternatives.

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