Skip to main content
Glama

create_track

Add a MIDI, audio, or return track to an Ableton Live Set and get its address for loading devices or routing sends.

Instructions

Add a MIDI, audio or return track and say its address. A new return track gets the next letter (rB after rA); load an effect on it with load_device and send to it with update_track sends. One undo step.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_track"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNomidi, audio or return (a return track for sends).midi
nameNoTrack name. Empty: Live's default name.
indexNoWhere to insert, from 0. Empty: after the last track.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: the tool is a single 'One undo step' (useful for an agent planning rollback) and return tracks auto-increment their letter (rB after rA). It does not mention whether the new track becomes selected or what happens to existing send routing, which keeps it from a 5.

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 short sentences, front-loaded with the core action, and every sentence conveys information (creation, return-track naming, follow-up calls, undo cost). The phrase 'say its address' is slightly loose about what the return value actually is, but nothing is padded.

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 no output schema, the description partly compensates by stating the tool reports the new track's address, and the undo and return-letter notes resolve the main behavioral questions for a non-destructive write. Remaining gaps are minor: no mention of selection side effects or how the new track interacts with existing sends beyond the return-track hint.

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%, with each of kind/name/index already documented and an enum on kind, so the schema carries the parameter burden and baseline is 3. The description corroborates the kind values and adds return-track naming semantics, but says nothing extra about how 'index' behaves (e.g. insertion shifting, string vs numeric type) beyond the schema's own text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Add a MIDI, audio or return track', and immediately states the outcome ('say its address'). It also names the track kinds that map to the enum, so an agent can distinguish this creation tool from update_track, duplicate, or delete without opening the schema.

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?

It supplies next-step guidance ('load an effect on it with load_device and send to it with update_track sends'), which implies this tool is the prerequisite for those workflows. However, it never says when to choose create_track over alternatives such as duplicating an existing track, and gives no exclusion or prerequisite conditions for the tool itself.

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