Skip to main content
Glama

groove

Idempotent

List the groove pool and update a groove's grid, timing, quantize, random and velocity amounts, plus the Set's global Groove Amount, when Live's API can't create or clear grooves.

Instructions

Read the groove pool and tune its grooves: grid, timing, quantize, random and velocity amounts, and the Set's global groove amount.

Live's API cannot create or remove grooves, and cannot clear a clip's groove; it can only change the grooves already in the pool. Assign a groove to a clip with update_clip. Each field gets its own result line with what Live holds afterwards (Live ignores some invalid writes, so check "now"). 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": {
      "action": "<action>"
    },
    "name": "groove"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoFor update: grid of the groove: 1/4, 1/8, 1/8T, 1/16, 1/16T, 1/32.
nameNoFor update: a new name for the groove.
actionYeslist the pool, or update a groove or the Set's amount.
grooveNoFor update: the groove's number from 0 (see list) or exact name.
groove_amountNoFor update: the Set's global Groove Amount; the answer shows what Live holds.
random_amountNoFor update: Random, 0-100.
timing_amountNoFor update: Timing, 0-100.
velocity_amountNoFor update: Velocity, 0-100.
quantization_amountNoFor update: Quantize, 0-100.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only supply the generic safety profile (not read-only, not destructive, idempotent). The description adds substantial context beyond that: the immutable-pool constraint, that some invalid writes are silently ignored so the returned 'now' values must be read, the per-field result-line format, and that the whole call collapses into one undo step.

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?

Front-loaded with the one-line purpose, followed by constraints and the sibling hand-off; every sentence carries information. Slightly fragmented by hard line breaks mid-thought ('...global groove amount.' / 'Live's API cannot...'), but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still explains the return shape (one result line per field showing what Live holds) and warns that writes may be ignored. Combined with the mutation and undo disclosure, an agent has everything needed to call this correctly for both 'list' and 'update' actions.

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 each parameter already documents its own purpose, units, and ranges; the description's field list largely restates that. It adds only the implicit 'for update only' framing that the schema already carries, so baseline 3 applies.

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?

States a specific verb pair ('Read ... and tune') plus the exact resource ('the groove pool') and enumerates the tunable fields (grid, timing, quantize, random, velocity, global amount). An agent can distinguish this from update_clip, update_set, or read_set without opening any schema.

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

Usage Guidelines5/5

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

Explicitly bounds the tool: Live's API cannot create, remove, or clear grooves, and it routes the adjacent task ('Assign a groove to a clip') to update_clip. That is both a when-not-to-use statement and a named alternative, so nothing is left to inference.

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