Skip to main content
Glama

mcp_opendaw_apply_genre_humanization

Add genre-appropriate timing and velocity variations to arrangement tracks to humanize robotic MIDI. Jazz uses swing and loose timing, funk uses behind-the-beat pocket, electronic genres stay tight.

Instructions

Apply genre-aware humanization to arrangement tracks — makes programmed MIDI feel alive.

After creating an arrangement, notes are perfectly quantized — robotic. This tool applies genre-appropriate humanization: jazz gets loose timing and wide velocity variation, electronic genres stay tight with minimal variation, funk gets behind-the-beat pocket feel.

Each genre has a different humanization recipe:

  • Jazz: high timing variation (0.20), high velocity variation (0.20), swing 0.66 (classic jazz swing feel). Drums get the most humanization.

  • Funk: behind-the-beat timing (positive bias), medium velocity variation, swing 0.0 (straight 16ths but with pocket feel).

  • Rock: medium timing (0.10), medium velocity (0.12), no swing. Drums get slight push, bass stays tight.

  • Reggae: laid-back timing (positive bias, behind beat), medium velocity, no swing. Bass stays tight (it's the lead), drums get loose.

  • Pop: very subtle (0.05 timing, 0.08 velocity), no swing. Pop should sound polished, not loose.

  • DnB/House/Techno/Trance/Synthwave/Dubstep/Trap: minimal humanization. Electronic genres should sound tight and consistent. Timing 0.03, velocity 0.05, no swing.

  • Afrobeat: medium timing (0.12), medium velocity (0.15), no swing. Polyrhythms need some human feel but stay grounded.

  • Disco: subtle timing (0.06), medium velocity (0.10), no swing. Disco should sound tight but not robotic — live drummer feel.

genre: One of: dnb, house, trap, techno, dubstep, afrobeat, rock, jazz, pop, funk, reggae, synthwave, trance, disco unit_index: AU index with the arrangement tracks. drum_track / bass_track / harmony_track / melody_track: Track indices. has_4th_track: True if arrangement has 4 tracks (False for 3-track genres).

Returns humanization parameters applied per track.

Example:

After: create_jazz_arrangement(...)

apply_genre_humanization("jazz", unit_index=0)

After: create_dnb_arrangement(...)

apply_genre_humanization("dnb", unit_index=0, has_4th_track=False)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
genreYes
bass_trackNo
drum_trackNo
unit_indexNo
melody_trackNo
harmony_trackNo
has_4th_trackNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

No annotations exist, so the description fully informs behavior. It details per-genre humanization (timing variation, velocity, swing) and notes that it affects tracks (drum, bass, harmony, melody). It mentions returns, but not reversibility. Still, transparency is strong given the informative genre recipes.

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?

The description is lengthy but well-structured: purpose, context, detailed genre recipes, parameter list, and example. Each section serves a purpose, especially the genre recipes which are essential for correct use. Could be slightly more concise (e.g., table for genres), but overall earns its length.

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 the output schema exists and the description mentions returns, the description is fairly complete. It explains all 7 parameters, provides examples, and gives extensive genre context. Missing some nuance on track indices, but adequate for the tool's complexity.

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 0%, so the description must compensate. It lists parameters (genre, unit_index, drum_track, etc.) and explains genre values and their effects. However, it does not fully explain each track index's role beyond name and example, and 'unit_index' is only briefly described. Adding more detail would improve parameter understanding.

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?

The description clearly states the tool's purpose: 'Apply genre-aware humanization to arrangement tracks — makes programmed MIDI feel alive.' It uses specific verb (apply) and resource (genre humanization on arrangement tracks). It distinguishes from siblings like 'humanize_notes' by focusing on genre-aware, whole-arrangement humanization.

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 description explains when to use: after creating an arrangement when notes are 'perfectly quantized — robotic.' It provides genre-specific humanization recipes, implying context. However, it does not explicitly state when not to use or list alternatives among siblings, but the genre-awareness provides clear guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AMEOBIUS-team/opendaw-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server