Skip to main content
Glama

audio_normalize

Normalize audio clip levels using peak or loudness modes, setting target dBFS or LKFS/LUFS, and optionally process clips independently instead of relative.

Instructions

Normalize audio clip levels. mode: one of the timeline's normalize modes (e.g. 'Sample Peak Program', 'True Peak Program', 'ITU-R BS.1770-4', 'EBU R128' — see result.modes). target_level dBFS for peak modes, target_loudness LKFS/LUFS for loudness modes (e.g. -14 for YouTube, -23 broadcast). independent=true sets each clip separately instead of relative.

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": {
      "clips": "<clips>"
    },
    "name": "audio_normalize"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoSample Peak Program
clipsYes
independentNo
target_levelNo
target_loudnessNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full load, and it does disclose real behavior: independent=true processes clips separately instead of relatively, plus the mode/unit split. It does not say whether normalization is destructive or undoable, how defaults behave (the schema's target_level default of -1 is unexplained), or what happens if the wrong target field is supplied for a mode.

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?

One dense block that front-loads the purpose and then walks parameters in a fixed pattern, with essentially no filler. It borders on a run-on and would read faster with light segmentation, but every clause carries information.

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

Completeness3/5

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

For a five-parameter mutation tool with zero annotation coverage, zero schema descriptions, and no output schema, the description covers the tuning parameters well but leaves the required 'clips' argument and the destructive/undo semantics unaddressed. It is adequate to call the tool, not complete for calling it safely.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate, and it does for four of five parameters: mode (with four concrete values and a pointer to the authoritative list), target_level (dBFS, peak modes), target_loudness (LKFS/LUFS with practical values), and independent (per-clip vs relative). The gap is the sole required parameter, 'clips', which is never described in type or shape.

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?

The first sentence names a specific verb and resource: 'Normalize audio clip levels.' The scope (clip levels) plus the mode/level vocabulary makes it distinguishable from adjacent audio tools such as audio_sync or clip_properties 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 Guidelines3/5

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

It gives conditional guidance inside the parameter walkthrough (peak modes with target_level, loudness modes with target_loudness, -14 for YouTube vs -23 for broadcast), which implies how to configure the call. However, it never states when to choose this tool over alternatives or when not to use it, and the 'see result.modes' pointer is an undefined reference rather than a real alternative.

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