Skip to main content
Glama

sketch_song

Build a genre-based song starting point in one call: tempo, drum groove, bassline, chords, and melody as editable MIDI loops for later arrangement.

Instructions

Builds a genre sketch in one call: tempo, then tracks with a drum groove, bassline, voiced and comped chords and a melody, all following the genre's profile (progression, harmonic rhythm, voicing, comping, bass style, melody density and scale, swing). Every part is ordinary MIDI to edit afterwards. It's one loop repeated: a starting point for a song, not the arrangement.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoKey with any scale or mode: 'A minor', 'F# dorian', 'Bb', 'Eb mixolydian', 'C harmonic minor'
barsNoLength of the sketch in bars (the loop repeats)
seedNoChange for a different melody and variations
genreYesAny genre from list_genres
partsNoDefault: all four
tempoNoBPM; default: the genre's typical tempo if the project is empty, else the project's
start_barNo
instrumentsNoPlugin per part from list_installed_fx, e.g. {'drums': 'SILA', 'bass': 'Mini V', 'chords': 'Analog Lab V', 'melody': 'Pigments'}; parts without one get an empty track
progressionNoChords or numerals to use instead of the genre's favourite

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.19.1

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are present, so the description bears the full burden. It usefully discloses that output is ordinary MIDI that can be edited afterwards and that the result is one repeated loop rather than an arrangement. It does not state side effects such as what tracks/items get created, whether existing project content is overwritten, or what happens to parts lacking a plugin (only the schema mentions empty tracks).

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 action and its outputs, and every sentence adds something (what is built, what profile drives it, editability, loop/arrangement scope). The first sentence is dense with a long parenthetical, but nothing is redundant.

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?

For a 9-parameter creation tool with no annotations and no output schema, the description conveys the outcome, the driving genre profile, and the editability/loop-scope caveat well. Remaining gaps are side-effect details (track/item creation, empty-track behavior) that an agent would still want before calling.

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 89%, so the schema already documents nearly every parameter (key, bars, seed, parts, tempo, instruments, progression). The description adds no parameter-level syntax or format detail beyond what the schema provides, so the baseline 3 is appropriate.

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 first sentence states a specific verb (Builds) and resource (a genre sketch) and enumerates exactly what is produced: tempo, drums, bassline, voiced/comped chords and melody. The genre-profile parenthetical and the closing sentence further pin down scope, so an agent can distinguish it from narrow siblings like write_bassline or add_drum_pattern.

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 rather than stated: 'It's one loop repeated: a starting point for a song, not the arrangement' tells the agent this is a scaffolding tool, not a full arrangement generator, which is useful scoping. However, no sibling alternatives (add_genre_groove, write_bassline, write_melody, add_chord_progression) are named and there is no explicit when-to-use/when-not-to-use guidance.

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

Deploy Server

Other Tools