Skip to main content
Glama

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

Identify a sound

doseedo_identify_sound

Instrument recognition + genre classification of audio (a stem, a loop, a whole mix): instrument (e.g. "sub_bass", "drum_machine", "synth_lead", "string_section"), family, render (the doseedo_render_midi fields that play it), write (how its part is written), candidates[], resembles[] (what it sounds like without being it: a synth lead that resembles a brass section), confidence, notes {low, high, most} (its register), genre[] (top 3), character {tone bright|dark, drive clean|driven, length short|sustained, weight}, reads (playful | neutral | sleek: does it sound like a toy advert or a cartoon?) + playful 0–1, tags[] (AudioSet) and measured {rms_dbfs, centroid_hz, low_share, onsets_per_s}. USE THIS on a reference track and on each of its stems (doseedo_separate_stems returns stem_identity already) before writing: you cannot hear, and tempo and key say nothing about the SOUND. Run it on your own mix too and compare genre and character with the reference. A whole mix: read genre and character (instrument names only its loudest element). A silent stem answers silent:true — nothing to copy there. Pass audio_key (an upload) or audio_url (a result URL from another job as returned, or any public https URL). Up to 10 minutes of audio is analyzed. Synchronous (~1–5 s), no credits. Cancel: not applicable — the result is returned in the submit response; the job is already finished.

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_identify_sound"
  }
}

Input Schema

NameRequiredDescriptionDefault
wantNoWhich answers to compute (default all three).
audio_keyNoR2 ingest key of an uploaded audio file (from doseedo_get_upload_url / POST /api/upload/r2/ingest-url; starts with "ingest/"). Provide this or audio_url.
audio_urlNohttps URL of the audio (a doseedo result URL as returned — a stem, a take — or any public URL). Alternative to audio_key.
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. Added

TDQS

A4/5.0
Behavior3/5

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

The description adds real operational context beyond annotations: synchronous ~1-5 s, no credits, a 10-minute audio cap, and an explicit statement that cancellation does not apply because the result returns in the submit response. However, it says nothing about failure modes beyond silence, rate limits, or what happens when the URL is invalid, and it leaves the readOnlyHint=false annotation unexplained even though the tool appears to be a pure analysis operation. Good added context, but not full behavioral disclosure.

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 content is valuable, but the opening sentence is a dense run-on that packs the entire return structure (instrument, family, render, write, candidates, resembles, confidence, notes, genre, character, reads, tags, measured) into one sprawling enumeration that is hard to scan. The genuinely actionable guidance — when to use, input alternatives, limits, silent stems — is buried after that wall of field names rather than front-loaded.

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?

With no output schema, the description does the necessary work of enumerating return fields, and it covers latency, credit cost, the 10-minute cap, input alternatives, cancellation semantics, and the silent-audio edge case. It is largely complete for a synchronous analysis tool; the main omission is parameter-level guidance for 'want' and any error/validation behavior.

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 the baseline is 3. The description adds some value by clarifying that audio_url may be 'a result URL from another job as returned, or any public https URL' and that audio_key is an upload, and it contributes the 10-minute limit. But the 'want' parameter — which controls whether instrument/genre/character are computed — is never mentioned in the description at all.

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?

Opens with a specific compound verb+resource: 'Instrument recognition + genre classification of audio (a stem, a loop, a whole mix)'. It names the output dimensions concretely (instrument, family, genre, character, notes register) and explicitly contrasts with tempo/key analysis, which separates it from doseedo_analyze_song and doseedo_analyze_midi.

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?

Gives explicit when-to-use instructions ('USE THIS on a reference track and on each of its stems ... before writing'), a follow-up use ('Run it on your own mix too and compare genre and character with the reference'), and a scoping rule for whole mixes vs single elements. It also anticipates a failure mode ('A silent stem answers silent:true — nothing to copy there') and notes that doseedo_separate_stems already returns stem_identity, which prevents redundant calls.

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