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

Without annotations, the description carries the burden of behavioral disclosure. It explains that the tool adds random cent offsets based on a seed (reproducible), and it states the return format. However, it does not disclose whether the operation is destructive or how it interacts with the original pitch data (e.g., whether it replaces or offsets), and there is no mention of undo or side effects.

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 action, followed by a brief context, then parameter docs and examples. The four-bullet 'Useful for' list is concise and practical, and the parameter explanations are dense without padding. It avoids redundancy despite its length.

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?

For a 6-parameter tool with no annotations and no schema descriptions, the description documents all parameters, provides defaults, ranges, return types, and examples. The main gap is the lack of a destructive/undo warning, which would be important for a pitch-modifying operation. The output schema likely covers the return object, so the return description is supplementary.

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 define the parameters. It does so thoroughly: unit_index/track_index/region_index scoping, cents_depth with levels (3=subtle warmth, 5=natural, etc.), bias with direction, and seed reproducibility. This goes far beyond the schema's bare names and defaults.

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 'Add micro-detune (cents) to notes — intonation humanization,' using a specific verb and resource, and immediately distinguishes itself from the sibling humanize_notes by noting that 'humanize_notes handles velocity/timing/duration, but pitch stays quantized.' This clearly sets it apart from related tools.

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?

It explicitly names the alternative for velocity/timing/duration (humanize_notes) and provides a 'Useful for' list of concrete scenarios (string sections, vocal MIDI, brass, sterile MIDI). This gives a clear context for when to apply the tool and what it does not do.

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