Skip to main content
Glama

get_midi_note_removal_context

Read-onlyIdempotent

Read a MIDI clip's notes, timing, target identity, and safety details before deleting notes in Ableton Live Session or Arrangement clips.

Instructions

Read complete notes, timing, native target identity and safety for explicit note deletion from a Session/Arrangement MIDI clip. Read-only, up to 4096 notes without sampling; all profile.

Input Schema

NameRequiredDescriptionDefault
clipIdYeslist_clips Session ID or supported list_arrangement_clips ID.
trackIdYesID from list_tracks.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.3.1
    • 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": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "clipTiming": {
      +        "type": "object"
      +      },
      +      "deviceId": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "editContext": {
      +        "type": "object"
      +      },
      +      "identityToken": {
      +        "type": "string"
      +      },
      +      "notes": {
      +        "items": {
      +          "properties": {
      +            "duration": {
      +              "type": "number"
      +            },
      +            "mute": {
      +              "type": "boolean"
      +            },
      +            "noteId": {
      +              "type": "integer"
      +            },
      +            "pitch": {
      +              "maximum": 127,
      +              "minimum": 0,
      +              "type": "integer"
      +            },
      +            "probability": {
      +              "maximum": 1,
      +              "minimum": 0,
      +              "type": "number"
      +            },
      +            "releaseVelocity": {
      +              "maximum": 127,
      +              "minimum": 0,
      +              "type": "integer"
      +            },
      +            "start": {
      +              "type": "number"
      +            },
      +            "velocity": {
      +              "maximum": 127,
      +              "minimum": 0,
      +              "type": "integer"
      +            },
      +            "velocityDeviation": {
      +              "type": "integer"
      +            }
      +          },
      +          "required": [
      +            "noteId",
      +            "pitch",
      +            "start",
      +            "duration",
      +            "velocity",
      +            "mute"
      +          ],
      +          "type": "object"
      +        },
      +        "type": "array"
      +      },
      +      "reason": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "removeSupported": {
      +        "type": "boolean"
      +      },
      +      "setFingerprint": {
      +        "type": "string"
      +      },
      +      "stateVersion": {
      +        "minimum": 1,
      +        "type": "integer"
      +      },
      +      "status": {
      +        "type": "string"
      +      },
      +      "supported": {
      +        "type": "boolean"
      +      },
      +      "trackId": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "stateVersion"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "properties": {
      +      "error": {
      +        "properties": {
      +          "message": {
      +            "type": "string"
      +          },
      +          "outcome": {
      +            "enum": [
      +              "unknown",
      +              "not_executed"
      +            ]
      +          }
      +        },
      +        "required": [
      +          "message",
      +          "outcome"
      +        ],
      +        "type": "object"
      +      }
      +    },
      +    "required": [
      +      "error"
      +    ],
      +    "type": "object"
      +  }
      +]
  2. Addedv0.3.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description reinforces this with 'Read-only'. It adds genuine behavioral context beyond annotations: a hard cap of 4096 notes and 'without sampling', which tells the agent results are complete rather than truncated. The vague 'all profile' phrase slightly muddies this.

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 purpose and appends the safety/scale constraints. It wastes little space, though 'native target identity and safety' and 'all profile' are jargon-y and less informative than plain phrasing.

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?

An output schema exists, so return-value explanation isn't required, and annotations cover the safety profile. The description supplies the clip scope, the 4096-note completeness guarantee, and the read-only nature, leaving little an agent needs missing apart from explicit sibling/alternative routing.

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 coverage is 100%, so both trackId and clipId are already documented as ID sources. The description refers to 'Session/Arrangement MIDI clip' and 'native target identity', loosely corroborating the clipId/trackId pairing, but it adds no syntax or format detail beyond the schema. 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 uses a specific verb (Read) with a concrete resource (complete notes, timing, native target identity and safety) and a stated purpose (explicit note deletion from a Session/Arrangement MIDI clip). It implicitly frames itself as the pre-flight read for deletion, distinguishing it from insertion, but never names a sibling like get_midi_clip_notes or get_midi_note_insertion_context explicitly.

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?

'for explicit note deletion' implies the use case (gather context before remove_midi_notes), but the description gives no explicit when-to-use/when-not guidance and does not point to alternatives such as get_midi_clip_notes (full note dump) or get_midi_note_insertion_context. Usage must be inferred.

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

Deploy Server

Other Tools