voice_to_piano_roll

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

With no annotations provided, the description carries the full burden. It clearly discloses that the tool records audio, transcribes it using pyin or Spotify Basic Pitch, writes notes to the piano roll, and returns results including a WAV path. It also mentions optional scale snapping, quantization, and the clear_first behavior. However, it does not explicitly state that the tool is write-only (mutates the project) or that permission may be needed for mic input.

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 well-structured with a one-liner summary, then an Args section, then a Returns section. It is front-loaded with a sentence that immediately conveys the tool's high-level function. While the Args block is lengthy, it is necessary for the 11 parameters and is clearly formatted.

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?

Given the high parameter count (11), lack of output schema, and absence of annotations, the description is remarkably complete. It covers all parameters, explains return values, and even notes dependencies (polyphonic extra). It leaves little ambiguity about how the tool operates or what the agent should expect.

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 input schema has 0% coverage, so the description must explain all parameters. It does so comprehensively in the Args block, detailing each parameter's purpose, acceptable values, defaults, and constraints (e.g., quantize_grid_sec examples with BPM, polyphonic dependency). This fully compensates for the schema's lack of 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 starts with a clear and specific verb+resource: 'Hum/play a melody into the mic, get it written straight into FL's piano roll.' This immediately and precisely communicates the tool's purpose, distinguishing it as an audio-to-MIDI tool for FL Studio.

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 provides no guidance on when to use this tool versus its siblings, such as 'audio_melody_to_piano_roll' or 'voice_record_and_transcribe.' It does not state prerequisites, limitations, or scenarios where alternatives would be preferred.

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