Execute any cocut command to edit a shared video timeline, enabling live collaborative changes with undo support.
Run any cocut command (without the leading 'cocut'), e.g. "text 'Hello' T1 2 3 --y .8", "set size+=4 --track T1", "split 12.5", "gen title V2 0 --params '{"text":"Hi"}'", "layers c1a2b3 --text-clips", "undo". See help.
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | the cocut command line, without 'cocut' |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses that arbitrary commands are executed, but does not mention side effects, whether commands can modify or destroy project state, permissions required, output format, or error behavior. Examples like 'undo' and 'split' imply mutation but safety context is absent.
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, followed by illustrative examples. The single sentence with examples is efficient, though the inline examples make it slightly denser than necessary.
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 generic command executor with no output schema, the description explains command formatting and points to `help`. However, it omits return-value behavior, error handling, and safety context, leaving gaps an agent would need to infer or test.
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% and already describes the single `command` parameter. The description adds meaningful value with concrete examples of command syntax ('text ...', 'set size+=4 ...', 'undo'), clarifying format beyond the schema's minimal description.
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: 'Run any cocut command'. The examples clarify the scope of commands. It points to the `help` sibling for command help, but does not explicitly differentiate itself from `show` or `assets` beyond the generic execution role.
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?
Usage is implied through examples and the note to omit the leading 'cocut'. The 'See `help`' pointer routes agents to a sibling for command help, but there is no explicit guidance on when to use `run` versus `show` or `assets`.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.