Skip to main content
Glama

plan_cuts

Builds a reviewable cut plan from silences, filler words, retakes, and manual transcript cuts, returning a planId and summary to approve before applying edits.

Instructions

Build a cut plan (which parts of the source to keep) from silences, filler words (um/uh…), retakes (restarted sentences) and your own manualCuts chosen from the transcript. Nothing is changed in the editor yet: returns a planId and a summary to review with the user, then call apply_cuts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "plan_cuts"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
modelNoWhisper model. "base" (default) is fast; "small"/"medium"/"large-v3-turbo" are more accurate but slower. Downloaded on first use.
minKeepNoDrop kept pieces shorter than this, seconds (default 0.25)
paddingNoBreathing room kept around speech at each cut, seconds (default 0.08)
languageNoISO language code such as "en" or "fr"; default auto-detect.
manualCutsNoExtra SOURCE-time ranges to remove
minSilenceNoShortest pause to remove, seconds (default 0.5)
fillerWordsNoOverride filler list, e.g. ["um","uh","you know"]
thresholdDbNoSilence threshold dBFS (default -35)
removeFillersNoDefault true (needs a transcript; transcribes automatically)
removeRetakesNoDefault false. Cuts earlier attempts when a sentence is restarted within ~10s.
removeSilencesNoDefault true

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations present, the description carries the burden and does deliver the critical disclosure: 'Nothing is changed in the editor yet,' which tells the agent this is a non-mutating preview. It also discloses the return shape (planId plus a summary) and that review with the user comes first; it does not mention the cost/latency of the implicit transcription pass mentioned in the schema, which is the main remaining behavioral gap.

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 sentences, front-loaded with the deliverable and ending on the safety/next-step clause. No filler, no restating of the tool name.

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 12-parameter tool with no output schema and no annotations, the definition covers purpose, side-effect posture, and return values well. It could go further on how the returned plan is inspected or revised (show_plan) and on the automatic transcription side effect of filler removal, which is the one thing an agent might surprise a user with.

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 coverage is 92%, so parameter documentation is already largely handled by structured fields, and the description adds only framing (that manualCuts come 'from the transcript' and are source-time ranges the schema already labels). It does not clarify interactions among the twelve knobs, e.g., how removeFillers depends on a transcript or how minKeep interacts with padding.

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

Purpose5/5

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

States a concrete verb and artifact — 'Build a cut plan (which parts of the source to keep)' — and enumerates the four inputs that shape it (silences, filler words, retakes, manualCuts). It is clearly distinguishable from its sibling apply_cuts, which is named outright.

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

Usage Guidelines4/5

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

Gives a clear workflow context: it produces a reviewable plan, changes nothing yet, and the next step is apply_cuts. It stops short of explicit exclusion conditions (e.g., when to re-plan vs. inspect an existing plan or when to skip planning entirely), so it is clear but not exhaustive.

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