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

Adds real context beyond annotations: the gap is left (not closed), clips may be cut as well as removed, changed enumerates each clip with its track, and a warning fires when audio went with the picture. That is useful disclosure. However, the annotation destructiveHint=false is arguably in tension with a tool that permanently removes clips – the description doesn't clarify whether this is undoable, which is exactly the question an agent would have.

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?

Front-loaded with the core action and scope, then default behavior, then return/warning behavior. It is one dense sentence chain with parenthetical nesting; slightly awkward to parse but every clause carries information.

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?

Covers the default track scope, the locking alternative, what gets reported in changed, and the audio-with-picture warning; output schema handles return shape. What's missing is any statement about reversibility/undo, which matters most for a destructive-feeling range operation.

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%, so range, track_ids, preview and timeline_id are all documented in the schema. The description adds the meaningful default semantics for track_ids (all unlocked) and the interaction with track locking, but says nothing extra about preview or the end-exclusive range. Baseline 3 with a modest lift for the default-scope explanation.

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?

States a specific verb+resource: remove everything in a frame range on given tracks, leaving a gap. Distinguishes clearly from siblings clip.remove (single clip) and range.extract (which closes the gap), and the 'leaving a gap' phrase pins down the semantic difference.

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?

Explains the default scope (all unlocked tracks), why that matters (a picture range also takes the sound under it), and how to narrow it (lock a track with track.set, or name track_ids). It doesn't explicitly name range.extract or clip.remove as alternatives, but the when-to-use guidance for track scoping is concrete.

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