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

Annotations already flag destructiveHint=true and idempotentHint=false, so the safety bar is partly covered; the description adds genuinely non-structural behavior — linked A/V partners follow the edit, and extension is bounded by available source material. It does not say whether trimming leaves a gap or ripples subsequent clips, which is the main remaining unknown for a destructive timeline edit.

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?

Three sentences, front-loaded with the action, then the parameter semantics, then the constraint. The example is the only 'extra' and it carries the ambiguous sign convention, so every sentence earns its place.

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 six-parameter destructive mutation with no output schema, the description covers the two semantic parameters, the linked-clip side effect, and the failure boundary. The remaining gap is timeline-level consequence (gap vs ripple) and confirmation of return behavior, which matters for an agent reasoning about subsequent edits.

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%, but the schema is thin where it matters ('start | end', 'Signed frame delta for that edge'); the description resolves the sign convention and supplies a concrete example (edge 'end', delta -12 shortens by 12 frames). That is real disambiguation beyond the structured data, not repetition.

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 and resource ('Adjusts one edge of a clip') and immediately scopes it to a single in- or out-point, which separates it from move_clips, split_clips and remove_clips without needing to name them. An agent knows exactly what class of edit this performs.

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 operating convention for both parameters (edge 'start'/'end', delta sign with a worked example) and notes the source-material limit on extending. It stops short of naming alternatives or when-not-to-use cases (e.g. versus ripple_delete_ranges or move_clips), so it is clear context without explicit routing.

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