Skip to main content
Glama
Dorico Maestro

Dorico Maestro

add_marking

Places a dynamic or tempo marking at a chosen bar, staff, and beat without using Dorico’s popover, then verifies the new event was selected; set pickup when the flow starts with an upbeat.

Instructions

Write a dynamic or a tempo at a bar, staff and beat, without the popover.

Returns:
    Result dictionary with the command sent and ``verified`` when Dorico
    selected a newly created event of the expected type.

Note:
    Places the caret the way goto_bar does, then sends the popover's command
    with the text as ``Definition``: Dorico creates the item directly and
    selects it (Dorico Elements 6.2.40, dynamic measured and checked in an
    exported PDF). Mind the pickup flag: without it a flow that opens with a
    pickup gets the marking one bar early. Note input is left afterwards.

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": {
      "kind": "<kind>",
      "text": "<text>",
      "bar": "<bar>"
    },
    "name": "add_marking"
  }
}

Input Schema

NameRequiredDescriptionDefault
barYesBar number, counted from 1, so bar 1 is the first bar of the flow. Not an index.
beatNoBeat in the bar, 1-based.
kindYesdynamic (mf, sfz, ff) or tempo.
textYesWhat you would type in Dorico's popover: 'mf', 'pp<', 'Allegro q=120'.
staffNoStaff index, counted from 0, where 0 is the topmost staff in the current layout. Counted differently from a bar number on purpose: bars start at 1, staves at 0.
pickupNoTrue when the flow starts with a pickup (upbeat) bar. Dorico does not number it as bar 1, so bar navigation lands one bar short without this. Nothing in the API reveals a pickup, so ask the person whose score it is, or read an exported MusicXML file with read_score.

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?

Goes well beyond the annotations: discloses that it moves the caret like goto_bar, that Dorico creates and selects the item, that 'verified' is set only when the expected event type was selected, that note input is left afterwards, and warns about the pickup off-by-one-bar failure mode. The annotations only cover the mutation/safety profile, and the description supplies the operational context they omit.

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 a single clear purpose sentence, then structured Returns/Note sections. Some wording is dispensable, notably the parenthetical version-and-PDF verification detail ('Dorico Elements 6.2.40, dynamic measured and checked in an exported PDF'), which is noise for an agent.

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?

Despite an output schema existing, the description still summarizes the return dict usefully, and it covers the tricky pickup case, caret state, and post-call state for a moderately complex mutation tool. Only the absence of explicit sibling routing leaves a small gap.

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 coverage is 100% and the schema already documents bar/staff indexing conventions and the pickup flag in detail, so the baseline of 3 applies. The description reinforces the pickup consequence ('gets the marking one bar early') and explains that text is sent as the popover Definition, but this largely restates what the schema covers rather than adding new semantics.

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 and resource ('Write a dynamic or a tempo') plus the exact addressing dimensions (bar, staff, beat), and explicitly distinguishes itself from the popover-based alternative. An agent can tell it apart from open_popover without opening a schema.

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 phrase 'without the popover' implicitly routes to open_popover as the alternative, and the pickup note gives concrete recovery guidance ('ask the person whose score it is, or read an exported MusicXML file with read_score'). No explicit when-not statement, but context is clear.

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