Arrange a 4-piece band from a natural-language prompt. Returns conductor tempo/groove, 4 lanes of note events, lead sheet, and base64 MIDI. Audio render (Csound → WAV) stays on local thiri-conductor-mcp / POST /v2/render.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| durationSec | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already set readOnlyHint=true and destructiveHint=false, so the agent knows it is a safe read/generation operation. The description adds meaningful behavioral context by noting that audio rendering remains on a local endpoint (thiri-conductor-mcp / POST /v2/render), implying the tool returns data but does not perform the actual audio synthesis internally. This adds value beyond the annotations without contradiction.
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?
The description is compact, two sentences long, and front-loads the core purpose and return outputs. The second sentence adds a precise implementation detail about the external rendering endpoint, which is valuable for an agent to understand dependencies. There is no fluff or redundancy, making it highly efficient.
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?
The tool has 2 parameters, no output schema, and no per-parameter descriptions. The description covers the main purpose, the return payload (tempo/groove, 4 lanes, lead sheet, base64 MIDI), and the external render behavior. However, it lacks explicit definition of how 'durationSec' behaves or how the output is structured, which would improve completeness. Given the annotation coverage and the straightforward nature of the parameters, this is sufficient but not exhaustive.
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?
The schema has zero description coverage for parameters. The description gives partial meaning to 'prompt' by calling it a 'natural-language prompt', but it does not explain the optional 'durationSec' parameter at all. Since there are only two parameters, this substantial gap in parameter documentation is poorly compensated for by the description.
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 clearly states the tool's function: 'Arrange a 4-piece band from a natural-language prompt.' This uses a specific verb ('Arrange'), a specific resource ('a 4-piece band'), and outlines the return payload (tempo/groove, note lanes, lead sheet, base64 MIDI). It effectively distinguishes itself from the sibling chord-generation tools by focusing on full-band arrangement rather than chord analysis or voicing.
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?
The description implies usage for creating a band arrangement from natural-language prompts, but does not explicitly indicate when to prefer this over alternatives or provide any exclusion criteria. The sibling context (chord-focused tools) helps suggest differentiation, but the description itself lacks explicit usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation—analysis, resolution, voicing, reharmonization, and arrangement—and the descriptions clarify the boundaries well. The closest pair is analyze_chord and resolve_chord, both d chord-input tools, but one yields abstract theory (intervals, roman numerals) while the other yields concrete data (frequencies, MIDI, scales).
The set follows a consistent verb_noun snake_case pattern: analyze_chord, conduct_band, generate_voicing, resolve_chord. The lone deviation is reharmonize, a single verb with no explicit object, which breaks the pattern slightly but remains perfectly readable.
Five tools is well within the ideal 3-15 range for a domain-specific server. Each tool covers a distinct facet of harmonic work—analysis, realization, voicing, reharmonization, and arrangement—and none feels like filler.
The surface covers the core chord-intelligence lifecycle: parse, realize, voice, and transform chords, plus full arrangement via conduct_band. Minor gaps exist—there is no progression-analysis tool and no inversion-specific operation—but agents can work around them.