Skip to main content
Glama

set_device_params

Idempotent

Set one or more device or rack macro parameters by name using Live's display units or raw numbers, with per-parameter results and errors.

Instructions

Set one or more parameters of a device or rack macro, by name, in the units Live shows ("400 ms", "-6 dB", "50 %", "On") or as raw numbers.

Each parameter gets its own line: "now" is what Live shows afterwards, a wrong name comes back with similar names, and one failure never stops the others. If a parameter has automation, Live stops playing it (the answer warns; use transport re_enable_automation). One undo step.

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>",
      "params": "<params>"
    },
    "name": "set_device_params"
  }
}

Input Schema

NameRequiredDescriptionDefault
paramsYesParameters to set. Example: [{"param": "Release", "value": "400 ms"}, {"param": "Decay", "value": "1.2 s"}]
targetYesDevice address: t0/d0, t1/d0/c0/d1

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-destructive, idempotent, closed-world behavior, and the description adds genuine context beyond that: per-parameter result lines, an echoed 'now' value, partial-failure semantics ('one failure never stops the others'), similar-name suggestions on a bad parameter, automation being halted with a warning, and a single undo step. What remains unstated is whether the call is atomic across the array and whether any state or focus precondition is required.

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?

Purpose is front-loaded and every sentence carries information about behavior or failure modes with no padding. The phrasing around 'Each parameter gets its own line: "now" is what Live shows afterwards' is compressed to the point of needing re-reading, which costs some immediate clarity.

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 and only two top-level parameters, the description does the work of explaining what comes back (a line per parameter, the resulting 'now' value, warnings, similar-name suggestions) plus the side effect on automation and undo scope. It is complete enough to call correctly, with atomicity as the main open question.

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 supplies the example strings ('400 ms', '-6 dB') and the target address format (t0/d0, t1/d0/c0/d1), so the description mostly restates it. The only meaningful addition is confirming raw numbers are accepted alongside display text; it adds nothing about ordering, duplicate names, or index versus name precedence within the array.

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 verb and resource ('Set one or more parameters of a device or rack macro') and states the accepted value forms, so the operation is unambiguous. It does not, however, distinguish this tool from close siblings such as update_device or update_set, so an agent must infer the boundary from name alone.

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 the resource type (device/rack macro parameters) rather than stated. The one explicit alternative it names, 'use transport re_enable_automation', is a recovery step after automation is killed, not a when-to-use-this-instead-of-X rule, and no exclusions or prerequisites are given.

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