Skip to main content
Glama

Cut Idle Stretches

cut_idle
Destructive

Remove dead air: cut stretches where the screen is frozen (and silent), keeping a short pad. Returns the time saved.

Instructions

Remove dead air: cut stretches where the screen is frozen (and silent), keeping a short pad. Returns the time saved.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "input": "<input>"
    },
    "name": "cut_idle"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesPath to the source video.
actionNocut (default), or speed: fast-forward them.
dryRunNoOnly report what would be cut.
factorNospeed: times faster (default 8).
outputNoOptional output path. Defaults under SCREENCAST_HOME/edits.
keepSecNoSeconds kept at each edge of a cut (default 0.4).
useAudioNoRequire silent audio too (default true when there is audio).
overwriteNoAllow replacing an existing file at the output path (default false).
minIdleSecNoOnly cut still stretches at least this long (default 2).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.51.1
    • addedInput schema / properties / action
      Added value: +{
      +  "description": "cut (default), or speed: fast-forward them.",
      +  "enum": [
      +    "cut",
      +    "speed"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / factor
      Added value: +{
      +  "description": "speed: times faster (default 8).",
      +  "exclusiveMinimum": 1,
      +  "maximum": 100,
      +  "type": "number"
      +}
  2. Changed3 schema fields changedv0.47.0
    • changedInput schema / properties / dryRun / description
      Previous value: -"Only report the stretches that would be cut; write nothing."New value: +"Only report what would be cut."
    • changedInput schema / properties / keepSec / description
      Previous value: -"Keep this much of each stretch at both edges so cuts are not abrupt (default 0.4)."New value: +"Seconds kept at each edge of a cut (default 0.4)."
    • changedInput schema / properties / useAudio / description
      Previous value: -"Count a stretch as idle only if the audio is also silent (default true when the video has audio). Set false to cut frozen video even while sound plays."New value: +"Require silent audio too (default true when there is audio)."
  3. First observedv0.32.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered. The description adds useful specifics: what is removed (frozen and silent stretches), that a short pad is retained, and that the time saved is returned — though it omits that output defaults to a new file under SCREENCAST_HOME/edits and that overwrite is off by default.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core action front-loaded and the detection criterion immediately following. Nothing is redundant, and the return-value note is appended compactly rather than spelled out.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter destructive tool with no output schema, the description covers the core behavior and the return value, and the schema fills the rest at full coverage. It could still mention the non-destructive dryRun preview and that a new file is written by default, which matter for a destructive operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are already documented in structured form and the baseline is 3. The description only echoes the pad behavior ('keeping a short pad') without adding format, units, or interaction details beyond what keepSec and minIdleSec already state.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('cut') and a precisely defined resource ('stretches where the screen is frozen (and silent)'), which is enough to distinguish it conceptually from transcript-based siblings like cut_by_transcript. It stops short of naming any sibling explicitly, so differentiation is inferred rather than declared.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the use case (screencast footage with dead air) through the definition of what it detects, but gives no explicit when-to-use or when-not guidance and does not mention alternatives such as cutting by transcript. An agent must infer the context from the predicate alone.

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