ableton-mcp

Overview Schema Source Related Servers Discussions Admin

plan_midi_humanization

Read-onlyIdempotent

Plan deterministic, bounded timing and velocity humanization for exact MIDI note IDs while preserving expression metadata and rejecting new same-pitch collisions.

Instructions

Plan deterministic bounded timing and velocity humanization for exact MIDI note IDs. Preserves expression metadata and rejects new same-pitch collisions.

Input Schema

Name	Required	Description
`seed`	Yes	Deterministic humanization seed.
`clipId`	Yes	list_clips Session ID or supported list_arrangement_clips ID.
`noteIds`	Yes	Unique stable note IDs to humanize.
`trackId`	Yes	ID from list_tracks.
`gridBeats`	Yes	Reference grid step in beats, including fractional triplet values.
`maxVelocityOffset`	Yes	Maximum absolute velocity movement.
`maxTimingOffsetBeats`	Yes	Maximum absolute timing movement in beats; must not exceed half gridBeats.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.3.1Oct 23, 2026

changedInput schema / properties / clipId / description

Previous value: -"Session ID from list_clips; Arrangement ID from list_arrangement_clips where supported."New value: +"list_clips Session ID or supported list_arrangement_clips ID."

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / anyOf

Added value: +[
+  {
+    "properties": {
+      "clipId": {
+        "type": "string"
+      },
+      "context": {
+        "type": "object"
+      },
+      "plan": {
+        "properties": {
+          "changes": {
+            "items": {
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "newNotes": {
+            "items": {
+              "properties": {
+                "duration": {
+                  "type": "number"
+                },
+                "pitch": {
+                  "maximum": 127,
+                  "minimum": 0,
+                  "type": "integer"
+                },
+                "start": {
+                  "type": "number"
+                },
+                "velocity": {
+                  "maximum": 127,
+                  "minimum": 0,
+                  "type": "integer"
+                }
+              },
+              "required": [
+                "pitch",
+                "start",
+                "duration",
+                "velocity"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "noteIds": {
+            "items": {
+              "type": "integer"
+            },
+            "type": "array"
+          },
+          "notes": {
+            "items": {
+              "properties": {
+                "duration": {
+                  "type": "number"
+                },
+                "pitch": {
+                  "maximum": 127,
+                  "minimum": 0,
+                  "type": "integer"
+                },
+                "start": {
+                  "type": "number"
+                },
+                "velocity": {
+                  "maximum": 127,
+                  "minimum": 0,
+                  "type": "integer"
+                }
+              },
+              "required": [
+                "pitch",
+                "start",
+                "duration",
+                "velocity"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "preservedNotes": {
+            "items": {
+              "type": "object"
+            },
+            "type": "array"
+          }
+        },
+        "required": [],
+        "type": "object"
+      },
+      "stateVersion": {
+        "minimum": 1,
+        "type": "integer"
+      },
+      "trackId": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "stateVersion",
+      "trackId",
+      "clipId",
+      "context",
+      "plan"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "error": {
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "outcome": {
+            "enum": [
+              "unknown",
+              "not_executed"
+            ]
+          }
+        },
+        "required": [
+          "message",
+          "outcome"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

Changed3 schema fields changedv0.3.0Oct 19, 2026

changedInput schema / properties / clipId / description

Previous value: -"Stable clip ID: track-N:clip-M from list_clips, or track-N:arrangement-clip-M from list_arrangement_clips for tools that support Arrangement clips."New value: +"Session ID from list_clips; Arrangement ID from list_arrangement_clips where supported."

changedInput schema / properties / trackId / description

Previous value: -"Stable track ID returned by list_tracks."New value: +"ID from list_tracks."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedv0.1.0Sep 23, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuine context beyond that: results are deterministic via seed, offsets are bounded, existing expression metadata is preserved, and same-pitch collisions are rejected rather than silently created.

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, both load-bearing: the first defines the operation and its bounds, the second states the preservation guarantee and the rejection condition. Front-loaded with the core action and no filler.

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 annotations and an output schema present, the description covers determinism, bounding, metadata preservation and the collision failure mode. The remaining gap is what a rejected collision actually returns and how this plan is subsequently applied or discarded, which the output schema partially covers.

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 100%, so the schema already documents seed, gridBeats, maxTimingOffsetBeats, maxVelocityOffset and noteIds with constraints. The description reinforces 'exact MIDI note IDs' and the bounded/deterministic nature but adds no format or interaction detail beyond the schema.

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 verb and resource: plan bounded timing and velocity humanization for exact MIDI note IDs. Scope (deterministic, bounded) is clear, but the description never contrasts this with the apply-side sibling humanize_midi_notes, so the plan-vs-apply distinction rests on the naming convention alone.

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?

The word 'Plan' implies a dry-run/preview step ahead of applying, and the required seed/grid/max-offset parameters imply intent, but there is no explicit when-to-use, no prerequisite statement, and no named alternative such as humanize_midi_notes. Usage is inferable rather than stated.

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

Deploy Server