Skip to main content
Glama

Auto Duck

audacity_auto_duck
Destructive

Ducks a bed track under a voice track using native AutoDuck; use dryRun to list exact parameters and save a project backup first because changes are destructive.

Instructions

Destructively duck bed samples under speech using native AutoDuck; save a project backup first. The unselected voice must be the immediately following track below the selected bed; import the bed first, then voice. dryRun lists exact parameters/range. Use audacity_envelope_set for editable ducking or an existing track order.

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": {
      "bed": "<bed>",
      "voice": "<voice>"
    },
    "name": "audacity_auto_duck"
  }
}

Input Schema

NameRequiredDescriptionDefault
bedYesbed track index (0-based) or unique name; must immediately precede the voice track
endNo
startNo
voiceYesvoice track index (0-based) or unique name; must immediately follow the bed track
dryRunNo
duckDbNoattenuation applied to the bed, in dB
fadeUpNoouter fade-up duration, in seconds
fadeDownNoouter fade-down duration, in seconds
innerFadeUpNoinner fade-up duration, in seconds
thresholdDbNovoice detection threshold, in dB
maximumPauseNomaximum pause to bridge while ducking, in seconds
innerFadeDownNoinner fade-down duration, in seconds

Output Schema

NameRequiredDescriptionDefault
bedNo
scopeYes
voiceYes
dryRunYes
paramsYes
commandNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description reinforces this with an actionable "save a project backup first" instruction plus the non-obvious track-adjacency constraint and the dryRun inspection mode. It stops short of covering failure behavior or whether a partial duck can be undone, so it is strong but not exhaustive beyond the annotations.

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

Conciseness4/5

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

Four short sentences, front-loaded with the destructive warning and constraint before the alternative. Slight redundancy: "import the bed first, then voice" restates the adjacency rule the schema already encodes.

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 destructive tool with an output schema, this covers ordering, backup, dry-run verification and the editable alternative. It leaves open which tool actually creates the recommended backup and what happens if the adjacency precondition fails, minor gaps given the structured data already supplied.

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 75%, so the schema already documents bed/voice position rules, duckDb, fades, threshold and maximumPause. The description repeats the adjacency requirement and adds the only genuinely new semantics, that dryRun lists exact parameters and ranges, which warrants the baseline 3 rather than more.

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?

"Destructively duck bed samples under speech using native AutoDuck" names a specific verb, the exact resource relationship (bed under voice), and the underlying Audacity feature, so an agent can distinguish it from generic effect calls or from audacity_envelope_set without opening the schema.

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

Usage Guidelines5/5

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

It states prerequisites (save a project backup first, import bed before voice, voice must sit immediately below the selected bed) and names an explicit alternative with the condition that selects it: audacity_envelope_set when editable ducking or an existing track order is required.

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