modularsynth-mcp

Overview Schema Source Related Servers Discussions Admin

Set song

set_song

Destructive

Define a song arrangement by sequencing scenes, each played for a set number of bars, with optional looping; an empty list clears it and a Clock is required to count bars.

Instructions

Write the song: scenes played one after another, each for a number of bars (e.g. intro 4, verse 8, chorus 8, break 4, chorus 8). Up to 64 lines; an empty list removes the song. "loop": start again at the end (default true; otherwise the clocks stop). Needs a Clock in the patch to count bars.

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": {
      "lines": "<lines>"
    },
    "name": "set_song"
  }
}

Input Schema

Name	Required	Description	Default
`loop`	No
`lines`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.3.1Nov 2, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations flag destructiveHint=true, and the description earns that by disclosing exactly what is destroyed (empty list clears the song) and what loop=false does ("the clocks stop"). It does not state whether the write replaces an existing song wholesale or what happens if a named scene does not exist.

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?

Front-loads the core action, embeds the example inline instead of in a separate sentence, and packs the two edge cases (empty list, loop=false) plus the Clock prerequisite into a few dense lines with no filler.

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 2-parameter destructive mutation with a prerequisite dependency according to its annotations and no output schema, the description covers format, limits, default and removal semantics. The remaining gap is validation behavior: whether scenes must already be saved and whether a prior song is overwritten.

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?

With 0% schema description coverage, the description carries the burden and mostly succeeds: the "intro 4, verse 8" example explains the scene/bars pairing, the 64-line cap is repeated, and loop's default of true and its meaning are spelled out. The per-entry bar bounds (1-256) and whether `scene` must reference an existing saved scene are left unexplained.

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?

"Write the song: scenes played one after another, each for a number of bars" gives a specific verb and resource plus the data model, immediately distinguishing it from playback tools like play_song. It stops short of naming a sibling explicitly, so the contrast with play_song/set_notes is inferred rather than stated.

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?

Provides clear operating context: an inline example of the intended shape, "an empty list removes the song" as a special case, and the prerequisite "Needs a Clock in the patch to count bars." No explicit when-not or sibling routing (e.g. use play_song to start it) is given.

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