Skip to main content
Glama
Dorico Maestro

Dorico Maestro

playback_setup

Destructive

Change VST plugin slots, instrument routing, or expression maps and apply playback templates in Dorico, confirming destructive edits before they run.

Instructions

Change VST slots, an instrument's routing, or an expression map.

Returns:
    Result dictionary with the command sent, whether Dorico finished it, and
    whether a playback change was signalled; ``route`` also reports the
    endpoint and, where Dorico logs it, a verified MIDI thru change.

Note:
    Measured in Dorico Elements 6.2.40 on a test project. The project must be
    activated for playback, or a load is refused with ``kCommandNotAllowed``.
    Endpoint = 1024 × (slot − 1) + channel − 1, so slot 2 channel 1 is 1024; a slot
    that was replaced can leave instruments elsewhere, which read_playback_setup shows.

    Loading into a slot that holds a plugin replaces it, and the instruments
    routed to it lose their routing silently: route them again. Dorico logs
    "slot is already occupied by the same plugin" even for a load that worked,
    so that line is no failure signal. Removing a slot needs ``confirm=True``.

    ``apply_template`` rebuilds the whole setup from a playback template: it
    reloads the template's sounds and resets routing and expression maps, so it
    needs ``confirm=True``.

    An instrument id that does not exist is answered with kOK and changes
    nothing; read_playback_setup lists the ids of a saved project. ``verified`` is
    True only when Dorico's log shows the MIDI thru endpoint moving, which happens
    for the instrument Dorico monitors; otherwise it is None, not False.

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": "playback_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
slotNoVST instrument slot as Dorico's window numbers it; slot 1 is Dorico's click, so the first usable slot is 2. Ignored by apply_template.
actionYesWhat to change in the playback setup.
pluginNoload_plugin: plugin name or 32-digit class id, see list_plugins.
channelNoroute and set_expression_map: MIDI channel.
confirmNoTrue authorises a change that discards work or cannot be undone.
templateNoapply_template: playback template id; the default is Dorico's automatic one.playbacktemplate.auto
instrumentNoroute: Dorico's instrument id, see read_playback_setup.
expression_mapNoset_expression_map: map id (xmap.…) or name, see playback_state.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.8

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds substantial context beyond them: replacing a plugin silently strips routing from instruments, confirm=True is required for slot removal and for apply_template's full reset, a missing instrument id returns kOK and changes nothing, and the 'slot is already occupied by the same plugin' log line is a false failure signal. It also explains that verified is None rather than False when Dorico's log shows no MIDI thru movement.

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 front-loads the purpose, and the Returns/Note structure makes the dense caveats scannable. The Note block is long and stacks several unrelated warnings, but nearly every sentence carries operational information an agent would otherwise get wrong.

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, seven-action, eight-parameter tool, the description covers the failure modes, confirmation requirements, silent-no-op behaviour and verification semantics that matter most. An output schema exists so the return explanation is redundant but harmless, and nothing an agent needs in order to avoid damaging a project appears missing.

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 100%, so the baseline is 3, but the description adds genuine meaning: the endpoint formula 1024 × (slot − 1) + channel − 1 with a worked example, what confirm actually authorises, and that slot is ignored by apply_template. This goes beyond the schema's own parameter descriptions rather than restating them.

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?

Opens with a specific verb and three concrete resources (VST slots, instrument routing, expression maps), and the seven sub-actions are discoverable from the enum. It partially differentiates from siblings by pointing to read_playback_setup for inspection and list_plugins for plugin ids, but it never enumerates or distinguishes the actions it bundles, which is a gap for a multi-action tool.

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?

Gives real selection conditions: the project must be activated or the load is refused with kCommandNotAllowed, slot 1 is Dorico's click so begin at slot 2, and read_playback_setup is named for listing instrument ids. It still lacks an explicit 'use read_playback_setup instead when you only want to inspect' statement, leaving that inference to the agent.

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