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

The annotation only declares readOnlyHint=false. The description adds rich behavioral detail: exactly which properties mutate (in/out points), which remain invariant (position and length), and the failure modes including locked tracks and delta bounds with range feedback.

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?

It is front-loaded with the core definition, followed by applicability and then refusal cases. Every sentence carries operational value, and there is no filler despite the dense refusal list.

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 covers target types, the exact mutation, and refusal modes, which is enough to invoke the tool correctly. However, with no output schema, it does not describe the successful return or response, a minor gap for a mutating editor tool.

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 100%, so all three parameters are already documented. The description restates delta direction and clip target types, but adds little parameter-level meaning beyond the schema; the position/length invariance is behavioral rather than parameter semantics.

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 operation: moving a clip's or scene's in/out points by delta_ms while keeping position and length unchanged. The phrases 'without moving it' and 'position and length stay' distinguish this from move, trim, slide, and roll siblings, even though it does not name them explicitly.

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 clearly states valid targets (video/audio clips and scenes with finished video) and refusal conditions such as unknown ids, text/stills, missing footage, locked tracks, and out-of-range deltas. It does not name sibling alternatives such as studio.slide_edit or studio.roll_edit for adjacent editorial operations, so it falls short of a 5.

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