Skip to main content
Glama

Transcribe attachment

transcribe_attachment

Make a new score from an attached file. Audio or video is transcribed, the whole piece: 10 credits when it first opens (a band: its quoted price; 30 seconds or less: free). A PDF or image is read whole: also 10 credits (30 seconds or less: free). MusicXML, MIDI, ABC and Guitar Pro open free. An edited copy of an existing score is saved into that score.

Input Schema

NameRequiredDescriptionDefault
bpmNoQuarter notes per minute, only if user-supplied or source-established (dotted quarters times 1.5); otherwise detected.
fileYesThe attached file as the host gives it.
viewNostaff, jianpu (1 = the key, movable do), jianpu_fixed (1 = C, fixed do) or jianpu_melody (top line only).
previewNotrue: a free 30-second preview instead of the whole piece, only when the user asks to try one first.
providerNolocal (one instrument or voice), piano (solo piano) or mirelo (a band: uses credits, priced first).local
pro_optionsNoBand (Pro) rhythm and paper choices, each optional: only user-supplied or source-established ones. Pass a source-established time_signature: omission uses N/4 and never detects 6/8, 9/8 or 12/8. Otherwise timing performance (quantized snaps to a reliable beat), subdivision found by Pro, tempo follow (fixed: one tempo, at bpm), page_size a4.
replay_onlyNoTest accounts only: reuse an exact saved band result, never new processing.
review_instrumentsNoBand only: true (default) holds it for the instrument list before the price.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed20 schema fields changed
    • removedInput schema / $defs
      Removed value: -{
      -  "ProOptions": {
      -    "additionalProperties": false,
      -    "description": "Pro (Mirelo) rhythm and paper choices; each one left out keeps its default.",
      -    "properties": {
      -      "bpm": {
      -        "anyOf": [
      -          {
      -            "maximum": 300,
      -            "minimum": 30,
      -            "type": "number"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "default": null,
      -        "description": "The constant tempo for tempo fixed, sent to Pro as given; the result states the tempo written (time_grid.tempo_bpm)."
      -      },
      -      "page_size": {
      -        "anyOf": [
      -          {
      -            "enum": [
      -              "a4",
      -              "letter"
      -            ],
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "default": null,
      -        "description": "Paper of the supplier PDFs and MusicXML; a4 (default) or letter."
      -      },
      -      "subdivision": {
      -        "anyOf": [
      -          {
      -            "enum": [
      -              "automatic",
      -              "straight_sixteenths",
      -              "eighth_triplets",
      -              "sixteenth_triplets",
      -              "swing_eighths"
      -            ],
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "default": null,
      -        "description": "Rhythmic grid. Omit it to let Pro choose; it keeps straight sixteenths unless triplets are clear."
      -      },
      -      "tempo": {
      -        "anyOf": [
      -          {
      -            "enum": [
      -              "follow",
      -              "fixed"
      -            ],
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "default": null,
      -        "description": "follow (default) keeps the tempo changes of the playing; fixed writes one constant tempo, at bpm or else at the tempo Pro detects. A bpm given with the upload means fixed."
      -      },
      -      "time_signature": {
      -        "anyOf": [
      -          {
      -            "enum": [
      -              "2/4",
      -              "3/4",
      -              "4/4",
      -              "5/4",
      -              "6/4",
      -              "7/4",
      -              "9/4",
      -              "12/4",
      -              "6/8",
      -              "9/8",
      -              "12/8"
      -            ],
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "default": null,
      -        "description": "Omit it to let Pro find the meter (written as N/4); choose 6/8, 9/8 or 12/8 explicitly for a compound meter."
      -      },
      -      "timing": {
      -        "anyOf": [
      -          {
      -            "enum": [
      -              "performance",
      -              "quantized"
      -            ],
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "default": null,
      -        "description": "performance (default) keeps the played timing; quantized aligns notes to the beat when Pro finds a reliable beat grid, otherwise the result reports a fallback."
      -      }
      -    },
      -    "type": "object"
      -  }
      -}
    • removedInput schema / properties / bpm / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / bpm / default
      Removed value: -null
    • addedInput schema / properties / bpm / description
      Added value: +"Quarter notes per minute, only if user-supplied or source-established (dotted quarters times 1.5); otherwise detected."
    • addedInput schema / properties / bpm / type
      Added value: +"number"
    • addedInput schema / properties / file / description
      Added value: +"The attached file as the host gives it."
    • addedInput schema / properties / preview / description
      Added value: +"true: a free 30-second preview instead of the whole piece, only when the user asks to try one first."
    • addedInput schema / properties / pro_options / additionalProperties
      Added value: +false
    • removedInput schema / properties / pro_options / anyOf
      Removed value: -[
      -  {
      -    "$ref": "#/$defs/ProOptions"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / pro_options / default
      Removed value: -null
    • addedInput schema / properties / pro_options / description
      Added value: +"Band (Pro) rhythm and paper choices, each optional: only user-supplied or source-established ones. Pass a source-established time_signature: omission uses N/4 and never detects 6/8, 9/8 or 12/8. Otherwise timing performance (quantized snaps to a reliable beat), subdivision found by Pro, tempo follow (fixed: one tempo, at bpm), page_size a4."
    • addedInput schema / properties / pro_options / properties
      Added value: +{
      +  "bpm": {
      +    "maximum": 300,
      +    "minimum": 30,
      +    "type": "number"
      +  },
      +  "page_size": {
      +    "enum": [
      +      "a4",
      +      "letter"
      +    ],
      +    "type": "string"
      +  },
      +  "subdivision": {
      +    "enum": [
      +      "automatic",
      +      "straight_sixteenths",
      +      "eighth_triplets",
      +      "sixteenth_triplets",
      +      "swing_eighths"
      +    ],
      +    "type": "string"
      +  },
      +  "tempo": {
      +    "enum": [
      +      "follow",
      +      "fixed"
      +    ],
      +    "type": "string"
      +  },
      +  "time_signature": {
      +    "enum": [
      +      "2/4",
      +      "3/4",
      +      "4/4",
      +      "5/4",
      +      "6/4",
      +      "7/4",
      +      "9/4",
      +      "12/4",
      +      "6/8",
      +      "9/8",
      +      "12/8"
      +    ],
      +    "type": "string"
      +  },
      +  "timing": {
      +    "enum": [
      +      "performance",
      +      "quantized"
      +    ],
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / pro_options / type
      Added value: +"object"
    • addedInput schema / properties / provider / description
      Added value: +"local (one instrument or voice), piano (solo piano) or mirelo (a band: uses credits, priced first)."
    • addedInput schema / properties / replay_only / description
      Added value: +"Test accounts only: reuse an exact saved band result, never new processing."
    • addedInput schema / properties / review_instruments / description
      Added value: +"Band only: true (default) holds it for the instrument list before the price."
    • removedInput schema / properties / view / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / view / default
      Removed value: -null
    • addedInput schema / properties / view / description
      Added value: +"staff, jianpu (1 = the key, movable do), jianpu_fixed (1 = C, fixed do) or jianpu_melody (top line only)."
    • addedInput schema / properties / view / type
      Added value: +"string"
  2. Changed1 schema field changed
    • addedInput schema / properties / preview
      Added value: +{
      +  "default": false,
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: the credit cost model (10 credits, free for 30s-or-less, free for notation formats), the band/quote pricing caveat, and the side effect that an edited copy is written into the existing score. What it omits is the operational shape of the call — that processing is long-running, may need polling/cancellation, and can be cancelled — which matters given openWorldHint=true and a non-idempotent mutation.

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 core action, then organized by input type. Slightly padded: the "10 credits … (30 seconds or less: free)" formula is stated twice in near-identical form, which could be collapsed into one sentence without losing information.

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?

Given 8 parameters, nested objects, and no output schema, the description covers cost, free paths, and the edited-copy side effect well, and the creation of a score is implied. It stops short of saying what the agent gets back (a new score vs. an updated version, job/preview handles) and how a long transcription is tracked or cancelled.

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 bpm, view, preview, provider, pro_options and replay_only are all already documented in structured form. The description echoes a few of these indirectly ("a band" ~ provider=mirelo, "30 seconds or less: free" ~ preview) but adds no syntax or interaction detail beyond the schema, so the baseline 3 applies.

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?

Names a specific verb+resource ("Make a new score from an attached file") and then breaks down behavior by input type (audio/video transcribed, PDF/image read, MusicXML/MIDI/ABC/Guitar Pro opened), so an agent knows exactly what class of input this handles. It implicitly separates itself from transcribe_link/transcribe_music via "attached file", but never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the per-file-type breakdown and the note that edited copies save back into the existing score, which helps an agent pick this over a generic transcription tool for attachments. However there is no explicit when-to-use/when-not guidance against the many siblings (transcribe_link, transcribe_music, transcribe_again, rate/cancel tools), leaving the choice to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources