Converts chord symbols into pitch classes, note names, and close-position MIDI notes from the root, with an optional root octave for voicing.
Notes of a chord symbol (C, Am7, F#m7b5, Bbmaj9, G7/B, Dsus4, …): pitch classes, names and MIDI notes in close position from the root.
| Name | Required | Description | Default |
|---|---|---|---|
| octave | No | Octave of the root (4 = middle C's). | |
| symbol | Yes | Chord symbol. |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context by stating the returned voicing is 'close position from the root', which an agent cannot learn from the annotations or schema. It does not cover invalid-symbol handling, but that is a minor gap for a deterministic theory tool.
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?
A single front-loaded sentence naming the resource first, then what is returned, then the input domain. Every clause carries information; the example list is compact and earns its space by demonstrating valid syntax.
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?
With no output schema, the description correctly names the return contents (pitch classes, names, MIDI notes) and the voicing rule. What is missing is the shape of the return value (list vs object, note ordering, whether names correspond index-wise to MIDI numbers), which an agent consuming the result would want.
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 coverage is 100%, so the baseline is 3, but the schema's description of 'symbol' is only 'Chord symbol.' The description meaningfully compensates by showing the accepted syntax across roots, qualities, extensions and slash chords. The octave parameter is fully described in the schema and correctly left alone.
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 gives a concrete resource (the notes of a chord symbol) and enumerates exactly what is produced: pitch classes, names and MIDI notes. The parenthetical example list (C, Am7, F#m7b5, G7/B, Dsus4) pins down the input domain precisely. It stops short of naming a sibling like theory_scale or theory_harmonize, so it is clear but not explicitly differentiated.
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 only implied: an agent can infer this is the chord-to-notes lookup, distinct from theory_scale (scales) or theory_harmonize. There is no explicit when-to-use statement, no mention of alternatives, and no guidance on how this pairs with clips_write_midi or theory_progression.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.