split_clip

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

With no annotations, the description fully shoulders the behavioral transparency burden. It discloses what is preserved (static transforms, enabled state, color, grade layer), what is rejected (Fusion, mixed rates), what is not guaranteed (audio links/fades/metadata), and the failure mode (opens checkpoint, reports partial timeline). This is exemplary transparency for an operation with side effects.

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 slightly longer than minimal, but every sentence contributes distinct information: the operation, preservation guarantees, rejection cases, failure recovery, and usage cautions. It is well-structured, starting with the core purpose before diving into caveats. There is no redundancy, so the length is justified.

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?

Given the output schema exists (so return format is covered), the description provides essential context: prerequisites (checkpoint), constraints (normal-speed only, rejection of Fusion/mixed rates), side effects (preservation and non-guarantees), failure handling, and agent guidance (prefer unique IDs, verify results). This covers all critical aspects for an agent to invoke the split correctly.

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 clarify parameter meaning. It clarifies 'frame' and 'timecode' as an absolute split point, and 'item_id' is implied by the advice to use unique IDs from timeline_overview. However, 'track_index' is not addressed, and default values are left to the schema. The description adds some value but does not fully compensate for the missing schema descriptions.

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 specifies the operation: splitting a clip at an absolute frame/timecode, with the prerequisite of a timeline checkpoint. It distinguishes this action from sibling tools like delete_clips or set_clip_transform by focusing on the split operation. The mention of 'normal-speed' and the specific preservation details further clarifies the precise functionality.

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 gives strong usage constraints: it applies to normal-speed clips, rejects Fusion compositions and mixed rates, and warns about audio/metadata limitations. It does not explicitly name alternative tools for other cases, but the conditions are clear enough to guide agent selection. The advice to 'prefer unique IDs from timeline_overview' is also a usage directive.

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