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

With no annotations, the description carries the full transparency burden. It discloses detailed genre-specific behavior (timing/velocity/swing values), track-level effects (drums get most, bass stays tight), and that it returns the applied parameters. It does not explicitly state whether it mutates the actual MIDI notes or how it interacts with prior humanization, but the coverage is substantial.

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 a clear purpose statement, followed by structured sections: context, genre recipe bullets, parameter list, return value, and a concrete example. It is long, but every sentence contributes necessary behavioral or semantic detail for a complex tool with 7 parameters and 14 genres. Nothing feels redundant.

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 tool's complexity and the existence of an output schema, the description is remarkably complete. It covers the workflow context (post-arrangement), all parameter semantics, genre-specific recipes, track roles, and provides a usage example. The only minor omission is an explicit prerequisite statement, but the examples and opening context imply it clearly.

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 0%, so the description must compensate — and it does. It explains the genre parameter with an explicit list of allowed values, defines unit_index as 'AU index with the arrangement tracks', interprets the track indices, and clarifies has_4th_track in the context of 3- vs 4-track genres. This adds essential meaning beyond the bare parameter names.

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: 'Apply genre-aware humanization to arrangement tracks — makes programmed MIDI feel alive.' It clearly distinguishes itself from generic humanization tools (e.g., humanize_notes, apply_swing) by emphasizing genre-awareness and the arrangement-track context.

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 clear contextual guidance: use it after creating an arrangement because notes are quantized/robotic. Examples explicitly show calls after create_jazz_arrangement and create_dnb_arrangement. However, it does not explicitly name alternative tools to use instead (e.g., humanize_notes) or exclusion cases, so it stops short of perfect guidance.

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