LiveSession MCP

by Uri-Rosen

Overview Schema Source Related Servers Discussions Admin

Python

Local

humanize_clip

Destructive

Adds subtle random timing and velocity variations to an existing MIDI clip, making programmed parts feel less rigid.

Instructions

Loosen an existing MIDI clip: small random timing (beats) and velocity changes.

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": {
      "track_index": "<track_index>",
      "clip_index": "<clip_index>"
    },
    "name": "humanize_clip"
  }
}

Input Schema

Name	Required	Description	Default
`timing`	No
`velocity`	No
`clip_index`	Yes
`track_index`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.0.0Nov 7, 2026

TDQS

B3/5.0

Behavior3/5

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

The description usefully discloses the non-deterministic character of the operation ('small random ... changes'), which annotations do not convey. However, despite destructiveHint=true it never says the clip's existing note timings and velocities are overwritten and require undo to recover, nor does it explain how the timing/velocity amounts scale.

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 front-loaded sentence with no filler; the verb and the two affected properties come first. It is efficient, though terse enough that it leaves little room for the missing guidance.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. Still, for a destructive, non-deterministic mutation with four undocumented parameters, the description omits reversibility, defaults, and the audio-clip exclusion.

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

Parameters2/5

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

Schema description coverage is 0%, so all four parameters rely on bare titles. The description adds the unit for timing ('beats') and clarifies that the two numeric knobs control the randomization magnitude, but track_index/clip_index addressing and the meaning of velocity=8 (MIDI velocity units of jitter?) remain unstated.

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 action (randomize timing and velocity) on a specific resource type (an existing MIDI clip), which an agent can read without opening the schema. It stops short of distinguishing itself from close siblings such as quantize_clip, swing_clip, and transform_clip, which all operate on clips.

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?

'Existing MIDI clip' implies a precondition, but there is no explicit when-to-use guidance, no exclusion (e.g. not for audio clips), and no routing to the many sibling clip-transform tools. In a sibling set this dense with near-equivalents, the agent must infer the choice entirely.

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

Deploy Server