Skip to main content
Glama
MuseScore MCP Server

MuseScore MCP Server

by ghchen99

Render

render

Display the engraved score as an image to inspect layout details—chord symbols, markers, breaks, and spacing—or crop specific measures for closer review.

Instructions

Show the score as MuseScore engraves it, as an image: what get_score's text cannot show, such as overlapping chord symbols, marker placement, system and page breaks and spacing. page=N gives a whole page (for layout); measures='X-Y' crops those bars from their page at higher detail, with everything attached to them (chord symbols, texts, lyrics, markers), as they stand on their systems: the other bars of those systems are left blank, so a blank space before the first bar means the system starts earlier. Measures are positions in the score, as in get_score's '% m.N', not printed bar numbers: with a pickup bar, printed bar 49 is measure 50. The caption gives the printed numbers when they differ. Render again after a change to check it.

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": "render"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage to show (1-based). Defaults to page 1
measuresNoMeasures to show instead of a page, by position (as in get_score's "% m.N"), e.g. "5-8" or "5"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.2

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the burden and does well: it discloses the cropping behavior (other bars of the same systems rendered blank, leading blank space implies earlier system start), that the caption reports printed numbers when they differ, and that measure positions are not printed bar numbers. It does not mention cost/latency, error behavior for an out-of-range page, or how the returned image is delivered, which keeps it below a 5.

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, then mode behavior, then the numbering caveat. Dense and largely waste-free, though the middle sentences are long and clause-heavy, which slows parsing slightly on first read.

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 two-optional-parameter read tool with no output schema, the definition covers purpose, both modes, cropping semantics, caption contents and the numbering pitfall — the things an agent needs to call it and interpret the result. Minor gaps remain around failure cases and image delivery.

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

Parameters5/5

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

Schema coverage is 100%, so a baseline 3 would be acceptable, but the description adds meaning the schema lacks: the critical distinction that measures are positions ('% m.N') rather than printed bar numbers, illustrated with the pickup-bar case where printed 49 is measure 50, and that measures crops at higher detail relative to their page.

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 concrete verb and resource ('Show the score as MuseScore engraves it, as an image') and immediately sets itself apart from get_score by naming what the text output cannot convey (overlapping chord symbols, system/page breaks, spacing). An agent can distinguish it from the text-reading sibling without opening either 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 names the alternative (get_score's text) and the condition that selects this tool (visual/layout questions the text cannot answer), plus a workflow instruction: 'Render again after a change to check it.' Within the tool it also routes between the two modes: page=N for layout, measures='X-Y' for detail cropping.

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