generate_chord_progression

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

With no annotations, the description carries the full burden of behavioral disclosure. It does add useful traits: 'creates the clip if empty', 'If omitted, picks an idiomatic progression', and explains the rhythm variants. However, it fails to state whether writing into an existing clip overwrites or merges with existing notes, which is a critical behavioral detail for a mutation tool. This gap prevents a higher score.

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 starts with a one-sentence summary, then lists parameters in a scannable format. Each parameter has a terse, informative explanation with examples and defaults. The structure is front-loaded and eliminates fluff, making it easy for an agent to parse quickly despite the large number of parameters.

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 11 parameters, no annotations, and no output schema, so the description must cover a lot. It does cover all parameters, defaults, and even creation behavior. The only notable gap is the lack of any mention of return values or success/failure feedback, which would be useful given the absence of an output schema. Overall, it is nearly complete for a complex generative tool.

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 provides no parameter descriptions (0% coverage), so the description is essential. It meticulously explains every parameter: track_index, bars, clip_index, arrangement_start, progression (with example), chord_size, octave (with MIDI convention), voicing (with enum values), key, rhythm (with definitions), and even user_prompt. This fully compensates for the missing schema descriptions.

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 opens with a specific verb+resource action: 'Write a diatonic chord progression as MIDI notes into a clip.' This clearly distinguishes it from siblings like generate_bassline or generate_drum_pattern by focusing on harmonic progressions. The term 'diatonic' adds further specificity, making the tool's purpose unambiguous.

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 does not explicitly state when to use this tool versus alternatives like generate_bassline or scaffold_track. It provides parameter-level guidance (e.g., 'Pass exactly one of clip_index / arrangement_start') but no high-level use case or exclusion criteria. The intended usage is implied by the name and description, but no alternatives are mentioned.

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