Skip to main content
Glama

read_clip

Read-onlyIdempotent

Reads an Ableton Live clip’s notes, settings, and markers to inspect it before editing and verify changes made by write or update operations.

Instructions

A clip, Session (track + slot, or clip t0/s2) or timeline (clip t0/a1): name, length, loop, and under settings its color, mute, markers, launch mode and quantization, legato, scale, time signature and groove. An audio clip adds its file, warp mode, gain, pitch and warp markers. A MIDI clip lists every note with pitch name and number, start and length in beats, velocity, and (when not default) probability, velocity deviation and release velocity.

Use it before changing notes and to check what write_clip or update_clip did.

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": "read_clip"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipNoA clip by address instead of track and slot: t0/s2 (Session slot 2 of t0) or t0/a1 (the second timeline clip of t0, see arrangement list).
slotNoClip slot: the scene row, from 0. Example: 0 for the first scene.
trackNoTrack address of a Session clip, e.g. t0 (with slot).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the description's job is to add context. It does add value by explaining that settings fields appear only under certain conditions and that probability/velocity-deviation/release-velocity are shown only when non-default, but it says nothing about failure modes for a bad clip address or whether long MIDI note lists are truncated.

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?

The return payload is front-loaded by clip type, and every clause carries information about a field the agent will see. The phrasing is dense and occasionally awkward ('under settings its color...', the mid-sentence line breaks), but there is 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?

There is no output schema, so the description carries the burden of describing return values, and it does so thoroughly for both audio and MIDI clips. What it leaves out is the behavior when no identifier is supplied (all params default to empty) and error/limit behavior, which matters given the tool's complexity.

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% and the schema already documents both addressing forms (t0/s2 and t0/a1) and the track/slot pair. The description restates the same addressing conventions without adding new constraints, and since all three parameters are optional with empty defaults it never says what an empty call resolves to. Baseline 3 applies.

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 definition opens by naming exactly what a clip record covers (name, length, loop plus settings like color, mute, markers, launch mode) and splits audio vs MIDI payloads, so the agent knows this is a detail-read tool. It never states a verb directly ('reads/returns') and leans on the name for the action, which keeps it just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The closing line gives concrete timing: 'Use it before changing notes and to check what write_clip or update_clip did,' naming the two sibling write tools. It offers no explicit when-not or a pointer for cases like scanning many clips at once (arrangement), so the guidance is solid but one-sided.

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