Skip to main content
Glama
Dorico Maestro

Dorico Maestro

manage_flows

Destructive

List, add, rename, or delete flows in an open Dorico project by ID—including removing extra flows added by MusicXML import—and return the updated flow list.

Instructions

List, add, rename or delete flows of the open project by id.

Returns:
    Result dictionary with ``flows`` (flowID and flowName) read back after the
    change.

Note:
    Measured in Dorico Elements 6.2.40: renaming and deleting are refused in
    Write mode (``kCommandNotAllowed``), so this switches to Setup mode and back.
    Deleting opens a confirmation dialog that a person must answer in Dorico;
    this waits up to ``wait_seconds`` for the flow to disappear and says so when
    it has not. Deleting needs ``confirm=True``. Use it to remove the extra flow
    a MusicXML import adds.

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": "manage_flows"
  }
}

Input Schema

NameRequiredDescriptionDefault
flowNorename and delete: flow id from action='list'.
nameNorename: the new name.
actionNoList the flows, add one, rename one or delete one.list
confirmNoTrue authorises a change that discards work or cannot be undone.
wait_secondsNodelete: how long to wait for the person to confirm.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.8

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only flag destructiveHint/readOnlyHint=false; the description goes far beyond by disclosing that rename and delete are refused in Write mode and that the tool silently switches to Setup mode and back, that delete opens a human-answered confirmation dialog in Dorico, and that it polls up to wait_seconds and reports when the flow has not disappeared. These are non-obvious side effects and failure modes an agent could not infer from structured fields.

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?

The lead sentence is front-loaded and the Note is dense with useful caveats, but the 'Returns' stanza restates output that an output schema already provides, making it dead weight. Overall tight, with one removable block.

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?

For a destructive, human-in-the-loop mutation tool this covers everything that matters: mode-switching side effects, the confirmation requirement, the wait bound, and the outcome when confirmation never arrives. Return values are handled by the output schema, so omitting them here costs nothing.

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 description coverage is 100%, so baseline is 3. The description reinforces that 'confirm' gates deletion and that wait_seconds bounds the confirmation wait, but both points are already stated in the schema field descriptions, so it adds little new meaning.

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?

The opening sentence names a specific verb set (List, add, rename, delete) against a specific resource (flows of the open project) and states the identifier convention (by id). An agent immediately knows this is the CRUD surface for flows and nothing else, and no sibling tool in the catalog competes for that scope.

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?

The description supplies a concrete use case ('Use it to remove the extra flow a MusicXML import adds') and the precondition for destructive actions ('Deleting needs confirm=True'), which is genuine when-to-use guidance. It stops short of naming an alternative or stating when not to call it, so it misses the explicit-alternatives bar for a 5.

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