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

Annotations already declare readOnly=false and destructive=false; the description earns credit for explaining exactly what is replaced ('those frames in place (same ids and names)') and that 'the old images are kept and can be restored', which makes the non-destructive hint credible. It also discloses the zero-cost ('Free') trait, which is not in any structured field. It omits whether the call runs synchronously or returns a job to poll via check_generation, a notable gap for a re-processing 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?

Front-loads the cost and action, then the pipeline, then the mutation semantics, then the eligibility caveat — a sensible order. Dense but nearly every clause carries distinct information; the long compound sentences (especially the pipeline list of four format traits) could be tightened.

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 two-parameter mutation with no output schema, the description covers cost, eligibility, what changes, what is preserved (ids/names), reversibility, and the parameter default semantics. The only unresolved item, sync vs. async response, is minor given the sibling check_generation.

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 baseline is 3, but the description adds real meaning for frameIds: omitting it re-cuts 'every re-cuttable animation on the asset', clarifying that the default scope is filtered by eligibility, not literally every animation. The id parameter is left to the schema, which already documents it well.

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 ('Re-cut an asset's animations') and immediately names the source ('the videos Voidless stored when it made them') plus the output characteristics (cut-out, seamless loop, 30 fps, one size across facings). It clearly distinguishes itself from generate_animation_set, which it names as the prerequisite producer rather than an alternative.

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?

Gives an explicit eligibility gate: 'Only for animations made in an animation set (generate_animation_set) since Voidless started keeping their videos.' That tells the agent both the required origin and a recency limit. It stops short of saying what to do instead when the asset doesn't qualify (e.g. fall back to generate_animation_set), so it is not fully comparative.

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