Extract melody from audio (pyin/CREPE)

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

Annotations declare readOnlyHint=true and idempotentHint=true, indicating no state changes. The description adds that the tool 'Does NOT write to FL -- review first,' and explains the output structure with bridge_notes and confidence flags. No contradictions with annotations.

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?

Two sentences: first states core function and engine trade-off, second details output and important behavioral note. Every sentence is essential, with no redundancy or filler.

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 output schema existence and annotations, the description sufficiently covers tool behavior, engine selection, confidence filtering, and integration with sibling tool. It addresses key concerns for an extraction tool without over-explaining.

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% with descriptions. The description adds value by explaining that bridge_notes contains only confident notes based on min_conf, and that engine can override environment variable. It also emphasizes 'MONOPHONIC source' for the path parameter, reinforcing schema hints.

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 transcribes a monophonic melody to quantized notes, with engine selection (CREPE vs pyin). It distinguishes between accuracy and weight, making its purpose specific and distinct from siblings like fl_analyze_audio or fl_write_piano_roll_notes.

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 notes that only confident notes are placed in bridge_notes for use with fl_write_piano_roll_notes, and explicitly states 'Does NOT write to FL -- review first.' It implies monophonic source requirements from schema context, but does not explicitly list when not to use or provide alternative tools for polyphonic sources.

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