resolve_build_cut_variant

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

With no annotations, the description must carry the full burden. It discloses key behaviors: dry-run by default, original timeline unchanged, overlapping ranges allowed, and tracks behavior. However, it does not explain the effects of parameters like dry_run, open_variant, or carry_markers, nor does it mention return values or potential side effects. The description covers the core non-destructive nature but leaves significant behavioral aspects unspecified.

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?

The description is reasonably concise, about four sentences, and front-loads the main action. It mixes parameter explanations inline but remains readable. It could be better structured with separate sections for parameters, but it is not overly verbose and wastes little space.

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 tool with 9 parameters, no annotations, and no output schema, the description is incomplete. It covers the core operation and two parameters, but leaves out many parameters that affect behavior (e.g., dry_run, open_variant, carry_markers). It also doesn't specify what the function returns or any error conditions. An agent cannot fully understand how to use this tool correctly based on the description alone.

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 0%, so the description must compensate. It explains 'remove' (format with start_seconds, end_seconds) and 'tracks' (all vs spine) in detail, but ignores the other 7 parameters (dry_run, open_variant, carry_markers, min_keep_seconds, spine_track_type, new_timeline_name, spine_track_index). This leaves the majority of parameters undocumented, which is inadequate for a tool with 9 parameters.

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 clearly states the tool cuts listed ranges from carried tracks into a new timeline, which is a specific verb-resource pair. It distinguishes itself from sibling tools like resolve_build_rough_cut by emphasizing 'text-based / manual editing' and explicitly mentioning it creates a new timeline. The example with caption cues from resolve_get_transcript further clarifies its intent.

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?

The description provides clear usage context: it's for text-based/manual editing, and gives an example of using caption cues for removing filler words. It implies it should be used when precise manual cuts are needed, but does not explicitly name alternatives or state when not to use it. However, the example and the distinction from automatic tools are enough to guide an agent reasonably.

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