Skip to main content
Glama

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

Spot a video → cue sheet

doseedo_spot_video

SPOT A FILM: a video in, the music editor's cue sheet out — the first step of scoring to picture. Scene detection on EVERY frame, and it listens to the soundtrack (CPU, no credits): hard cuts frame-exact (dark, low-contrast footage included), fades, flashes and visual impacts; each shot's brightness, colour, warmth, contrast, motion and mood, with a keyframe JPEG per shot so you can SEE what it shows; SCENES — where the picture moves to a new place, at a cut or with none (a camera move, a dissolve) — each with its start, how it arrives, how fast the camera travels (pace) and a 640-px frame; and a storyboard: the whole film on one JPEG, a frame every few seconds; where dialogue is (Silero VAD) and loud audio hits; INTENSITY — the picture's energy (motion, cutting, camera, the sound) as sections [{start_s, end_s, level, rel: low | medium | high | peak}], and each scene's own: where the music steps up, settles and peaks; then cues placed where the picture wants music and the dialogue lets it (1M1, 1M2 …: start/end SMPTE timecode, emotion, energy, tension arc, hit points ranked by strength, a suggested bpm that lands them, and tempo_map_input — pass it to doseedo_tempo_map as is). It sees light, movement and editing, not meaning: read the scene frames and the storyboard for what each scene is about. Input: video_key (doseedo_get_upload_url accepts mp4/mov/m4v/webm/mkv) or video_url (public https), ≤ 2 GB and ≤ 3 h. Optional start_timecode (the first frame's, e.g. 01:00:00:00; default the file's own), coverage (0.05–0.98, default 0.55: how much of the film gets music), reel (cue ids M), keyframes (0–60), spotter. Async: job_id → doseedo_wait_task (~1 min for a 10-min 1080p reel). Next: doseedo_tempo_map per cue → write the notes → doseedo_render_score → doseedo_mix → doseedo_score_to_picture. Cancel: a spotting pass still queued never starts and one running stops within seconds; either way its credit is refunded and the job ends as canceled.

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_spot_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
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>.
reelNoReel number for the cue ids (default 1 → 1M1, 1M2 …).
spotterNoWho places the cues. "rules" (default): light, motion and editing, weighted by hand, at coverage. "model": a cue model trained on 200 human-scored films. It places the cues where a composer would, and gives each cue its tempo (suggested_bpm), dynamics marks (dynamics: pp–ff every 8 s), turns (where it comes in full or steps up or down) and hits. Its tempo_map_input lands the hits on a beat and the turns on a bar line. Without coverage it decides how much of the film gets music; cue_sheet.cue_model says what it decided.
coverageNoHow much of the film gets music (default 0.55). Raise it for wall-to-wall scoring (a trailer, an animation), lower it for a dialogue drama.
keyframesNoHow many shots get a keyframe JPEG (default 24; the longest shots first). 0 = no images at all (no scene frames, no storyboard).
video_keyNoR2 ingest key of the uploaded video (doseedo_get_upload_url with the file name, e.g. reel1.mp4; starts with "ingest/").
video_urlNohttps URL of the video, as an alternative to video_key (a public file URL, fetched directly; ≤ 2 GB).
cut_thresholdNoScene-change threshold at full contrast (default 0.3). Lower finds softer cuts, higher only the hardest.
start_timecodeNoSMPTE timecode of the first frame, HH:MM:SS:FF (";" before the frames = drop-frame at 29.97/59.94). Default: the file's embedded timecode, else 00:00:00:00.
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. Changed1 schema field changed
    • addedInput schema / properties / spotter
      Added value: +{
      +  "description": "Who places the cues. \"rules\" (default): light, motion and editing, weighted by hand, at coverage. \"model\": a cue model trained on 200 human-scored films. It places the cues where a composer would, and gives each cue its tempo (suggested_bpm), dynamics marks (dynamics: pp–ff every 8 s), turns (where it comes in full or steps up or down) and hits. Its tempo_map_input lands the hits on a beat and the turns on a bar line. Without coverage it decides how much of the film gets music; cue_sheet.cue_model says what it decided.",
      +  "enum": [
      +    "rules",
      +    "model"
      +  ],
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / name
      Added value: +{
      +  "description": "Optional: 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>.",
      +  "maxLength": 80,
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • changedInput schema / properties / keyframes / description
      Previous value: -"How many shots get a keyframe JPEG (default 24; the longest shots first)."New value: +"How many shots get a keyframe JPEG (default 24; the longest shots first). 0 = no images at all (no scene frames, no storyboard)."
  4. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false); the description adds substantial behavior beyond that: CPU-only soundtrack analysis with no credits, async job_id flow, ~1 min for a 10-min 1080p reel, and precise cancellation semantics (queued pass never starts, running stops within seconds, credit refunded, job ends canceled). The idempotency_key parameter makes the call conditionally idempotent, which sits in mild tension with idempotentHint=false, though it is opt-in rather than a true contradiction.

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?

It is front-loaded with the verb-and-resource statement, which is good, but the body is a single dense paragraph of em-dash-separated clauses that mixes output inventory, input constraints, pipeline routing and cancellation policy without paragraph breaks. Density is defensible for a ten-parameter tool, but the run-on structure makes the operational details (limits, cancel semantics) harder to locate than they need to be.

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?

There is no output schema, so the description must carry the return contract, and it does — shot attributes, keyframe JPEGs, scene objects with arrival/pace/640-px frames, storyboard, intensity sections shaped as [{start_s, end_s, level, rel}], and cue fields (SMPTE start/end, emotion, energy, tension arc, ranked hit points, suggested bpm, tempo_map_input). Combined with the async and cancellation notes, nothing an agent needs to call it and act on the result is missing.

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 all ten parameters are already documented; the description mostly restates defaults (coverage 0.55, keyframes, reel, start_timecode, spotter). It does add one thing the schema lacks — the ≤ 2 GB and ≤ 3 h input limits and the accepted container list (mp4/mov/m4v/webm/mkv) via doseedo_get_upload_url — plus the handoff note that tempo_map_input should be passed to doseedo_tempo_map as is, but that is marginal against a fully documented schema.

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?

"SPOT A FILM: a video in, the music editor's cue sheet out — the first step of scoring to picture" gives a precise verb, resource and pipeline position. It enumerates the concrete artifacts produced (hard cuts, fades, scene list with 640-px frames, storyboard JPEG, dialogue via Silero VAD, intensity sections, numbered cues) so an agent can distinguish it from doseedo_tempo_map, doseedo_supervise_cues and doseedo_score_to_picture 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 Guidelines5/5

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

It states its place as the first step of scoring to picture and spells out the downstream chain ("doseedo_tempo_map per cue → write the notes → doseedo_render_score → doseedo_mix → doseedo_score_to_picture"), plus the async handoff to doseedo_wait_task. It also tells the agent what it cannot do ("It sees light, movement and editing, not meaning"), which is an explicit boundary against expecting semantic interpretation from it.

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