losslesscut-mcp

Overview Schema Source Related Servers Discussions Admin

Audio levels

audio_levels

Read-only

Analyze loudness over time using EBU R128 LUFS windows, identify the loudest moments, and measure overall loudness for a specified media segment.

Instructions

Loudness over time (EBU R128, LUFS) in windows, the loudest moments (laughter, applause, shouting, drops) and the overall loudness.

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": {
      "path": "<path>"
    },
    "name": "audio_levels"
  }
}

Input Schema

Name	Required	Description
`end`	No	End of the part to analyse (default: end of file)
`top`	No
`path`	Yes	Absolute path of a file the user gave you
`start`	No	Start of the part to analyse (default: start of file)
`windowSeconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.0.0Nov 13, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral detail about what is produced: windowed loudness values, a set of loudest moments with example event types, and an aggregate loudness. It does not state cost/performance characteristics, output format, or how windowSeconds and top shape the result.

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?

A single dense sentence that front-loads the core measurement and then enumerates the three outputs. No filler or repetition. It is slightly terse for the number of concepts packed in, but every clause earns its place.

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?

With five parameters, 60% schema coverage, and no output schema, the description does the essential job of conveying what is returned (windowed loudness, top loudest moments, overall loudness). What remains missing is modest: output shape/units and the roles of top and windowSeconds. Adequate for an agent to call the tool correctly.

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 60%, with start, end, and path documented in-schema while top and windowSeconds carry no descriptions. The description partially compensates: 'in windows' hints at windowSeconds and 'the loudest moments' hints at top, but it never ties these to the parameters, defaults, or units. Baseline 3 is appropriate.

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?

The description names a specific resource and measurement standard: loudness over time (EBU R128, LUFS), loudest moments, and overall loudness. An agent can tell this is an audio-analysis tool distinct from siblings like detect_silence or detect_scenes. It lacks an explicit verb phrase (e.g., 'analyze the audio file at path'), which keeps it just below a 5.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no mention of alternatives such as detect_silence, and no statement of preconditions (e.g., file must be opened). Usage is only implied by the subject matter. An agent must infer that this is the tool for measuring loudness rather than for detecting silence or clipping.

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