split_clip

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

No annotations are provided, so the description must explain the mutation's side effects. It says 'splits a clip' but doesn't disclose whether the original clip is preserved, whether the timeline is modified, if it's undoable, or if there are side effects on the project (e.g., new clip created). For a destructive/edit operation, this is insufficient behavioral disclosure.

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 a single concise sentence that immediately states the action and key parameter. No fluff or redundancy. It could add a bit more context but is efficient.

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?

This is a destructive/mutating operation (splitting clips creates new clips and potentially removes the original), yet there are no annotations to indicate safety or side effects. The description doesn't mention whether the original clip is preserved, how the timeline is affected, or if there are any restrictions (e.g., clip must be in a sequence). Given no annotations and no output schema, the description should carry more weight, but it doesn't disclose these behaviors.

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?

The schema already provides 100% coverage for both parameters (clipId and splitTime) with descriptive text. The description adds little beyond the schema, just reiterating 'at a specific time point,' which doesn't add meaningful new details. Baseline of 3 is appropriate.

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 verb (splits) and the resource (a clip) at a specific time point)SkipThe purpose is clear and distinguishes from sibling tools like 'trim_clip' or 'ripple_delete' which imply different operations. However, 'split' could be interpreted as creating two clips vs. cutting, but overall it's sufficiently clear.

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?

No guidance on when to use this tool versus alternatives like 'razor_all_tracks' or 'trim_clip'. It doesn't specify prerequisites (e.g., clip must be in timeline) or mention that this creates two separate clips with handles, which is useful context for an agent deciding between split and trim.

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