music_theory

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

Annotations already declare this is a read-only, idempotent, non-destructive, closed-world computation. The description adds two traits annotations cannot express: it never touches the Live set ('without touching Live') and it fixes the MIDI octave convention (C3 = 60), which materially affects numerical results. It says nothing about error handling for invalid chord/scale names, keeping it below a 5.

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

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

Purpose and the octave convention are front-loaded, then one compact clause per operation. Every phrase earns its place, including the illustrative literals that double as format documentation. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, multi-operation tool with no output schema and no schema descriptions, the description covers the operation matrix and sketched return shapes ('-> pitches', '-> MIDI number, names, frequency') well. Defaults (octave=3, octaves=1, voicing='close') and failure behavior for bad input names are left to the schema and inferred, so it is not fully self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 12 parameters, so the description must carry the load, and it largely does: it gives accepted forms for key ('A', 'F# dorian'), chord ('Am7', 'C/E', 'V7'), voicing values (close, open, drop2, drop3, spread), and the roles of inversion, octave, beats_per_chord and voice_leading. Gaps remain: the plural 'octaves' parameter and integer keys are never explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource (music theory utilities) and immediately enumerates the five operations with what each computes, including concrete input/output examples. The phrase 'without touching Live' cleanly separates it from the DAW-mutating siblings (write_notes, set_clip, etc.). An agent can tell what this tool does and what it does not.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Usage is conveyed per operation: use 'scale' with key+scale, 'chord' with a symbol or numeral, 'progression' to get chords and notes 'ready for write_notes', 'notes' to convert names/numbers, 'list' to discover valid scale/chord/voicing names. The mention of write_notes establishes the downstream relationship. There is no explicit when-not-to-use or named alternative, so it stops short of a 5.

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