Sound Autotune

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

Without annotations, the description carries the full burden and does well: it discloses that a new wav is written next to the take or to out=, that it never overwrites, and that WORLD processing needs pyworld. It does not discuss error behavior when pyworld is missing or permission requirements, so it is not fully exhaustive.

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 front-loaded with the core operation and packed efficiently using semicolons and parentheticals. It is dense but every sentence contributes parameter or behavioral information; a little more structure around parameter definitions could improve readability.

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 8 parameters, no annotations, and an existing output schema, the description covers the critical behavioral and parameter semantics: output file behavior, non-overwrite, dependency, pitch target modes, and retune speed. It is nearly complete, with minor gaps around amount and explicit path expectations.

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%, so the description must compensate, and it explains several parameters meaningfully: key+scale, notes as [[start_s, midi_pitch, dur_s]] with times from file start, speed_ms thresholds, and formant in semitones. It leaves amount unexplained and only implies path semantics.

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?

States a specific verb and resource: auto-tune a recorded voice file, with pitch mapped to key/scale or an explicit note list. It also distinguishes itself from the track autotune effect by naming the related fx_help workflow, so an agent can identify the operation without opening the schema.

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?

Gives clear usage context: phone voice notes, mic takes, stems; pitch can come from key+scale or explicit notes; speed_ms values describe the intended retune character. It references fx_help type='autotune' as the track-effect analogue but does not explicitly state when not to use this tool versus alternatives.

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