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

With no annotations, the description carries full responsibility for behavioral disclosure and delivers comprehensively. It details each mode's exact behavior (multiply, add, set, quantize, legato), explicitly mentions clamping to min/max, quantize overriding value, and legato gap semantics. It also states the return value (count of notes modified and duration stats), providing a thorough behavioral contract.

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 detailed but well-organized: an introductory summary, a structured list of modes with clear definitions, parameter explanations, and a practical example block. Every sentence adds meaningful information; no filler or redundancy. The formatting with bullets and spacing enhances readability without bloating the content.

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 (8 parameters, 5 modes, clamping, quantize override), the description covers all necessary context: parameter meaning, mode behavior, defaults, and examples. The return value is also described, which, combined with the output schema, gives a complete picture. No significant gaps remain.

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 fully compensate for all 8 parameters. It does so by explaining every mode's effect on the value parameter, defining min/max as clamp range, region_index's -1 meaning, and quantize override behavior. The inclusion of concrete examples (e.g., mode=multiply with value=0.5) further clarifies parameter usage beyond the bare schema.

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's purpose: 'Scale the duration of all notes in a region' with an explicit scope (MIDI note length control). It distinguishes itself from siblings by referencing scale_velocity ('Like scale_velocity but for note durations'), making it immediately clear which operation it performs and how it differs from similar 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?

The description provides clear usage context: 'Useful for changing articulation globally — make all notes shorter (staccato feel), longer (legato feel), or snap to a grid.' It also names an alternative (scale_velocity) to clarify when this tool is not appropriate. While it doesn't explicitly enumerate when not to use it, the comparison to scale_velocity gives a strong implicit guideline.

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