cut_to_beats

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

With no annotations, the description carries the full burden and does well: it says a NEW sequence is created (original unchanged), that motion/scale/position/rotation is carried over, that music and other tracks are preserved, and that dryRun previews the plan. It omits error behavior and what the dryRun output actually contains, but the mutation profile is genuinely disclosed.

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, then the mechanics, then safety (original unchanged) and dryRun. Dense but every clause carries information; the inline Vietnamese gloss on the naming convention is justified because it is part of the observable output.

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 an 8-parameter mutation with no annotations and no output schema, the description covers the essential contract: what is created, what is preserved, what is not modified, and how to preview. Missing fine detail (minShot interaction with beat snapping, sequenceId vs sequenceName resolution) keeps it from a 5.

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 75%, and the description adds real meaning beyond it — 'every: 1 = each beat, 2 = every other, 4 = each bar' explains the counting semantics, and it notes the default copy name suffix in place of an explicit `newSequenceName`. `minShot` and the sequenceId/sequenceName precedence remain unexplained.

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 concrete verb and object — re-time a cut to the music — and precisely characterizes the output as a copy of the sequence with a naming convention. It differentiates itself from beat-adjacent siblings (detect_beats finds beats; this one re-times cuts to them) by describing the exact transformation on video-track clips.

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?

Clear context for when this applies: clips on the video track, with music on a specified audio track, and an explicit `dryRun` preview path. It does not name alternatives (e.g. detect_beats or rough_cut_by_cues) or state exclusions, so routing is inferred rather than spelled out.

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