Skip to main content
Glama
MuseScore MCP Server

MuseScore MCP Server

by ghchen99

Set Style

set_style

Change score style settings in MuseScore using internal key-value pairs; unknown keys are rejected while earlier valid changes stay applied, and new values are returned as read back.

Instructions

Change score style settings (Format → Style), given as {key: value} with MuseScore's internal keys. An unknown key is refused, and the settings before it stay applied. Returns each value as MuseScore reads it back after the change; check it with get_style or render when unsure.

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": {
      "styles": "<styles>"
    },
    "name": "set_style"
  }
}

Input Schema

NameRequiredDescriptionDefault
stylesYesStyle keys and their new values

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.2

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses the most important behavioral trait: the write is partial on failure — an unknown key is refused while earlier keys stay applied. It also states the return values are read back as MuseScore interprets them, which signals normalization. It omits persistence/undo semantics and any connection or permission prerequisite.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no filler: purpose and input shape first, failure behavior second, verification path last. Every sentence carries distinct information an agent needs.

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 single-parameter mutation tool this covers purpose, key format, failure semantics, and a verification path, and an output schema exists so return shape needs no elaboration. The remaining gap is that it never says whether changes must be saved or are undoable, which matters for a settings mutation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100% for the single nested object, but the description adds real meaning beyond it: the map is keyed by MuseScore's internal style key names, and invalid keys are rejected rather than ignored. That rejection rule is not expressible in the free-form additionalProperties schema, so the description earns credit above baseline.

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 ("Change") and resource ("score style settings") and anchors it to the UI location "Format → Style", so the agent knows exactly what domain of settings this mutates. It is clearly distinguishable from the read-side sibling get_style, which it names explicitly.

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 names the follow-up alternatives and the condition that selects them ("check it with get_style or render when unsure"), which tells the agent when this tool is insufficient on its own. It does not spell out a when-not-to-use case or prerequisites such as needing a connected MuseScore instance, but the routing guidance present is concrete.

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