midi_humanize

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

With no annotations, the description fully carries the burden and discloses the random behavior mechanism: each note shifted by ±timing_ms and velocity by ±velocity_amount. It also specifies defaults (timing_ms=15, velocity_amount=8), making the tool's mutational behavior completely transparent.

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 efficiently structured with a one-sentence overview, a bulleted list of typical values, and a numbered parameter list. Every sentence adds value, with no redundancy.

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?

While lacking output schema and annotations, the description sufficiently covers usage and parameters. It could clarify if it affects all takes or only the active take, and if there are side effects like undo state, but overall it is complete for typical use.

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?

Despite 0% schema description coverage, the description provides detailed explanations for each parameter: item_index is the global item index, timing_ms is max random shift in ms, velocity_amount is max random velocity offset. This fully compensates for the lack of schema 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 clearly states the tool adds random timing and velocity jitter to MIDI notes, with the purpose of making programmed MIDI less mechanical. It uses a specific verb-resource pair ('Add random timing + velocity jitter') and distinguishes from sibling tools like midi_quantize which serves a different purpose.

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?

Provides explicit typical values for strings/pads, drums, and piano, offering clear context for parameter selection. However, it does not explicitly state when not to use this tool or compare to alternatives like midi_quantize, though the usage examples imply the appropriate scenarios.

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