Skip to main content
Glama
cavi-ai

ableton-mcp

by cavi-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

inspect_producer_bus

Read-onlyIdempotent

Verifies an existing group or audio bus against a layered blueprint by reading ordered FX, child sources, routing, and instrument identity, so you can confirm the bus is correctly configured.

Instructions

Read an existing Group or ordinary audio bus, ordered FX, child sources and routing against a layered blueprint. Audio uses two matching snapshot passes; checks No Input, monitor In, Main output and child Track In routes. Optional pluginId selects an explicitly chosen Serum 2, Omnisphere or VPS Avenger instead of the blueprint's factory instrument; this verifies loaded identity, not preset or sound.

Input Schema

NameRequiredDescriptionDefault
targetYes
busKindNogroup (default) or ordinary audio bus.
childrenYesOne track for each blueprint child role.
busTrackIdYesID from list_tracks.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.1
    • removedOutput schema / additionalProperties
      Removed value: -true
    • addedOutput schema / anyOf
      Added value: +[
+  {
+    "properties": {
+      "busChain": {
+        "type": "object"
+      },
+      "busTrackId": {
+        "type": "string"
+      },
+      "children": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "limitation": {
+        "type": "string"
+      },
+      "matchesBlueprint": {
+        "type": "boolean"
+      },
+      "stateVersion": {
+        "minimum": 1,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "stateVersion",
+      "busTrackId",
+      "busChain",
+      "children",
+      "matchesBlueprint",
+      "limitation"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "error": {
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "outcome": {
+            "enum": [
+              "unknown",
+              "not_executed"
+            ]
+          }
+        },
+        "required": [
+          "message",
+          "outcome"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]
  2. Changed4 schema fields changedv0.3.0
    • addedInput schema / properties / busKind
      Added value: +{
+  "description": "group (default) or ordinary audio bus.",
+  "enum": [
+    "group",
+    "audio"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / busTrackId / description
      Previous value: -"Stable track ID returned by list_tracks."New value: +"ID from list_tracks."
    • changedInput schema / properties / children / items / 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"
+}
  3. Changed2 schema fields changedv0.2.0
    • addedInput schema / properties / children / items / properties / pluginId
      Added value: +{
+  "enum": [
+    "serum-2",
+    "omnisphere",
+    "vps-avenger"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / target / enum
      Previous value: -[
-  "layered-bass-system",
-  "layered-synth-system"
-]New value: +[
+  "layered-bass-system",
+  "layered-synth-system",
+  "layered-drums-system",
+  "layered-keys-system",
+  "layered-vocals-system",
+  "layered-guitar-system"
+]
  4. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real behavioral context: two matching snapshot passes for audio, the specific routes validated, and that pluginId verifies loaded identity rather than preset or sound. That extra context is genuinely useful beyond the annotations.

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?

Three front-loaded sentences that stay on task with little filler. The route-listing sentence is dense with domain jargon but earns its place by naming exactly what is validated.

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 values need not be explained, and annotations cover the safety profile. The description supplies the inspection logic and pluginId caveat, leaving only minor gaps around target blueprint semantics.

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 coverage is 75% and the description adds meaning where the schema is thin, notably explaining the pluginId parameter's intent (explicit instrument choice vs blueprint factory instrument, verifying identity not preset). It also clarifies the group-vs-audio bus distinction, though it does not elaborate on target or child role structure.

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: reads an existing Group or ordinary audio bus and inspects ordered FX, child sources and routing against a layered blueprint. This distinguishes it from siblings like inspect_producer_chain and inspect_producer_return_bus by scope, though it does not name them directly.

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?

Usage is implied by describing what gets checked (No Input, monitor In, Main output, child Track In routes), so an agent can infer it is a verification/inspection step. However, there is no explicit when-to-use guidance or routing away from the neighboring inspect_* tools.

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