Skip to main content
Glama

configure_device

Destructive

Read and set device-specific settings—playback mode, wavetable voices, modulation, rack chains, Drum Rack pads, collapsed state—and run actions like reverse or copy_pad on a Live device.

Instructions

Read, set and run the device-specific things that are not parameters: Simpler playback mode, sample, slices and warp actions; Wavetable voices, oscillator wavetables and modulation matrix; Drift and Meld voicing and modulation sources; Compressor sidechain source; EQ Eight mode; Hybrid Reverb impulse responses; Roar, Shifter, Spectral Resonator and Looper; rack chains, Drum Rack pads and copy_pad; a device's collapsed state and A/B compare.

Call it with only a target to see the settings (current value, options or range) and actions that target has on this Live. Settings are checked and read back: each gets its own result line, a value Live refuses says so, and the others still apply. Targets: a device, a rack chain (t0/d0/c1) or a Drum Rack pad (t0/d0/pC1, which writes to every chain on the pad). The actions reverse, crop, clear and delete_all_chains change content; one undo step undoes them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "target": "<target>"
    },
    "name": "configure_device"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoArguments of the action. Example: [{"name": "beats", "value": 4}]
actionNoOne action to run after the settings, e.g. reverse, copy_pad, set_modulation.
targetYesDevice, rack chain or Drum Rack pad address. Examples: t0/d0 (first device on t0), t1/d0/c1/d0 (first device in chain 1 of that rack), t2/d0/pC1 (Drum Rack pad C1), rA/d0, m/d0
settingsNoSettings to set. Example: [{"setting": "global_mode", "value": "M/S"}, {"setting": "oversample", "value": true}]. Leave empty, with no action, to list what this target offers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the destructiveHint/openWorldHint=false annotations, it discloses genuinely non-obvious behavior: settings are checked and read back, each gets its own result line, a refused value is reported while the others still apply (partial-success semantics), and the reverse/crop/clear/delete_all_chains actions mutate content but are undone by a single undo step. This is exactly the kind of information an agent needs before invoking a destructive tool that may partially fail.

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 discovery instruction is front-loaded in the second sentence, and the partial-failure and undo statements are compact and high-value. The opening paragraph is a long run-on enumeration that could have been tightened, but each listed domain genuinely widens the tool's scope, so almost every item earns its place.

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?

For a high-complexity, destructive, multi-mode tool with no output schema, the description covers discovery mode, per-setting result reporting, partial failure, mutation scope and undo depth. Remaining gaps are minor: it does not say whether reads require the device to be selected/visible, nor give a hint about the shape of the result lines an agent must parse.

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 target formats, args, action and settings examples; baseline is 3. The description does add a little real meaning — that a pad target like t0/d0/pC1 writes to every chain on the pad, and that an empty settings/action combination means discovery — but it does not explain argument naming per action or the relation between args and action beyond the schema's own example.

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 opens with a specific scope statement: reading, setting and running device-specific settings that 'are not parameters', then enumerates the concrete domains (playback mode, wavetable voices, modulation matrix, sidechain, EQ mode, rack chains, Drum Rack pads, collapsed state). That 'not parameters' clause implicitly carves it away from set_device_params/update_device, so an agent can place it. The triple verb 'read, set and run' plus the very long enumeration slightly blurs the single-sentence purpose, keeping 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?

It gives a concrete usage pattern: 'Call it with only a target to see the settings (current value, options or range) and actions' — a discovery-then-apply workflow that an agent can follow directly. It also states that leaving settings empty with no action lists the target's offerings. It never names set_device_params as the alternative for ordinary parameters, so the exclusion is implied rather than stated.

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