Skip to main content
Glama

Doseedo Film Score: spot a video, play your score on AI instruments, mix it to picture

Cut cues from public-domain scores

doseedo_supervise_cues

MUSIC SUPERVISION, for a film whose direction is classical or orchestral: instead of writing every note, each cue is CUT FROM A REAL PUBLIC-DOMAIN SCORE (~1,000 orchestral pieces, Baroque to late Romantic, free to use in a film — no rights holds, no ShareAlike). The search fits each cue: its length to the frame (a passage bent ≤ ~17 % in tempo, cut on a bar line where it must), the cue sheet's turns on the score's own section changes, its hits on real accents, its mode and meter, its level over time (a quiet cue thins a tutti's doublings; the loudest moment lands on the source's own rise), and cues of one piece play fresh bars. SAY WHO PLAYS AND HOW BUSY IT IS, or a quiet piano-and-strings cue is cut from a tutti: instruments = the cue's players (the source plays only its parts for those); density = sparse | moderate | busy | driving, or notes a second; per film, or per_cue. Input: spot_job (the doseedo_spot_video job id — spotter "model" gives each second its level) or cue_sheet; cues (ids, default every score cue); direction {era: ["Baroque"|"Classical"|"Romantic"…], genre, composer: ["Antonín Dvořák"…], mode: major|minor}; prefer {cue: file} = take that cue from an alternative an earlier answer listed. Async: job_id → doseedo_wait_task (~5–60 s; a bad direction, cue or prefer fails at once), CPU, no credits. Result per cue: source {composer, title, licence, credit — the line a CC BY edition asks for}, edit (bars, stretch, cuts), render {score_url, instruments, name} = the doseedo_render_score call that plays it (pass it as is; change an instrument by editing instruments), mix_lufs_offset_db (master the cue at the delivery loudness plus this: doseedo_mix target_lufs), alternatives [{composer, title, file, cost}]. Cancel: the plane has no stop for a running catalogue search — it runs to completion (credits spent), the job ends as canceled and its output is discarded. Only a job still queued at the plane is refunded by the plane's own failure refund.

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": "doseedo_supervise_cues"
  }
}

Input Schema

NameRequiredDescriptionDefault
cuesNoOnly these cue ids (default: every score cue, ≤ 40).
nameNoOptional: a name for this job's files, e.g. "rainy-loop-3". Every file it returns downloads as <name>_<part>.<ext> (rainy-loop-3_Celesta.wav, rainy-loop-3_rough-mix.wav; one take: rainy-loop-3.wav), so the user can find them. Give each job its own name (a second take: "rainy-loop-3b"). Default: doseedo-<last 6 characters of the job id>.
preferNo{cue id: catalogue file}: cut that cue from this piece (a file an earlier answer listed under alternatives).
densityNoHow busy every cue is, on the parts that play: notes a second, or sparse (~2) / moderate (~4.5) / busy (~8) / driving (~13). Music under speech is sparse.
per_cueNo{cue id: {instruments?, density?}} — one cue's own players and density.
spot_jobNoThe doseedo_spot_video job id (job_…): its cue sheet is read for you (MCP tool only; the jobs API takes cue_sheet).
cue_sheetNoAlternative to spot_job: a cue sheet {video: {duration}, cues: [{id, kind?: "score", start_s, end_s, suggested_bpm?, turns?: [{time_s}], hits?: [{time_s}], dynamics?: [{at_s, mark}], instruments?: [names], density?}], cue_model?: {level_db_per_s}} — doseedo_spot_video's, or your own cue plan in its shape.
directionNoSteer the choice: era / genre / composer as a name or a list of names (the catalogue's own, e.g. era "Romantic", composer "Pyotr Ilyich Tchaikovsky"), mode "major" | "minor" for every cue.
instrumentsNoThe players every cue is cut for (a cue's own instruments win): "violin", "cello", "piano", "harp", "horn", "strings"… The source plays only its parts for these; an asked instrument it lacks is named on the card (ensemble.missing).
idempotency_keyNoOptional. Any unique string for THIS request (e.g. a UUID). Re-sending the same call with the same key after a timeout returns the same job instead of starting a second one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / cue_sheet / description
      Previous value: -"Alternative to spot_job: a cue sheet {video: {duration}, cues: [{id, kind?: \"score\", start_s, end_s, suggested_bpm?, turns?: [{time_s}], hits?: [{time_s}], dynamics?: [{at_s, mark}]}], cue_model?: {level_db_per_s}} — doseedo_spot_video's, or your own cue plan in its shape."New value: +"Alternative to spot_job: a cue sheet {video: {duration}, cues: [{id, kind?: \"score\", start_s, end_s, suggested_bpm?, turns?: [{time_s}], hits?: [{time_s}], dynamics?: [{at_s, mark}], instruments?: [names], density?}], cue_model?: {level_db_per_s}} — doseedo_spot_video's, or your own cue plan in its shape."
    • addedInput schema / properties / density
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "enum": [
      +        "sparse",
      +        "moderate",
      +        "busy",
      +        "driving"
      +      ],
      +      "type": "string"
      +    }
      +  ],
      +  "description": "How busy every cue is, on the parts that play: notes a second, or sparse (~2) / moderate (~4.5) / busy (~8) / driving (~13). Music under speech is sparse."
      +}
    • addedInput schema / properties / instruments
      Added value: +{
      +  "description": "The players every cue is cut for (a cue's own instruments win): \"violin\", \"cello\", \"piano\", \"harp\", \"horn\", \"strings\"… The source plays only its parts for these; an asked instrument it lacks is named on the card (ensemble.missing).",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / per_cue
      Added value: +{
      +  "additionalProperties": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "density": {
      +        "anyOf": [
      +          {
      +            "type": "number"
      +          },
      +          {
      +            "type": "string"
      +          }
      +        ]
      +      },
      +      "instruments": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "description": "{cue id: {instruments?, density?}} — one cue's own players and density.",
      +  "type": "object"
      +}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only cover readOnly/idempotent/destructive/openWorld; the description adds genuinely load-bearing context beyond them: async job_id → doseedo_wait_task, a ~5–60 s runtime, CPU with no credits, immediate failure on a bad direction/cue/prefer, and the whole cancel story (no stop for a running catalogue search, credits spent, output discarded, only queued jobs refunded). That is exactly the behavioral detail annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and nearly every clause carries information, but the body is a single dense run-on paragraph mixing all-caps emphasis, parentheticals and return-value documentation, which makes scanning hard. Some asides (render changing instruments, per-cue alternatives) border on duplicating schema descriptions.

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 10-parameter, nested-object, async job tool with no output schema, the description covers the full lifecycle: inputs, the wait handoff, the per-cue result shape (source/credit, edit, render, mix_lufs_offset_db, alternatives), and cancellation/refund semantics. An agent has enough to call it and to interpret the answer without further discovery.

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; the description earns above it by explaining why instruments and density matter ("SAY WHO PLAYS AND HOW BUSY IT IS, or a quiet piano-and-strings cue is cut from a tutti") and what prefer does ("take that cue from an alternative an earlier answer listed"). It does not restate every field, but the ones it touches gain real operational 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?

"each cue is CUT FROM A REAL PUBLIC-DOMAIN SCORE" names the exact verb and resource, and the opening clause ("MUSIC SUPERVISION, for a film whose direction is classical or orchestral: instead of writing every note") separates it from a generate-music sibling without the agent needing to open a schema. The catalogue scope (~1,000 orchestral pieces, Baroque to late Romantic) further pins down what the operation produces.

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?

It states the condition for use (a film with classical/orchestral direction) and the contrast case ("instead of writing every note"), plus which input path to take: spot_job from doseedo_spot_video or a cue_sheet. What it lacks is an explicit "do not use this if..." or a named alternative tool such as doseedo_generate_music, so the exclusion is only implied.

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