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

With no annotations provided, the description bears full responsibility for behavioral disclosure. It goes beyond a simple statement by enumerating the exact statistics returned (note count, pitch range, velocity stats, density, pitch class histogram, etc.) and showing an example output shape. It implies read-only behavior via 'Get statistics' but doesn't explicitly state that no modifications occur. It also doesn't mention edge cases like empty regions or invalid indices, but for a stats tool this level of detail is strong.

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 structured with a clear introductory sentence, a bullet list of statistics, a compact 'Useful for' list, parameter definitions, and a short example. It conveys substantial information without being bloated. The bullet lists are easy to scan and every sentence carries meaning. It is slightly longer than necessary but well organized.

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 moderate complexity, the description is complete. It covers purpose, output contents, use cases, and all parameters. The output schema (statistics object) is supplemented by the detailed field list in the description, making return values clear. No critical information about when or how to use this tool is missing.

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?

The input schema has 0% parameter description coverage, leaving the description to explain all parameters. The description explicitly covers each parameter: 'unit_index: AU index. track_index: Note track index. region_index: Region (-1 = first region).' This fully compensates for the schema gap and adds clarity beyond the bare integer types. The example call also helps clarify usage.

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: 'Get comprehensive statistics for notes in a region.' It clearly identifies the tool's function as a read-only analysis operation on MIDI note content. The scope is precise and distinguishes it from sibling tools like analyze_melody or analyze_track, which target different aspects.

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 a 'Useful for' list that gives clear context for when to use the tool (analyzing imported MIDI, comparing regions, identifying register, detecting programming issues). It doesn't explicitly state when not to use it or mention alternative tools, but the use cases strongly imply appropriate scenarios. It lacks exclusionary guidance like 'use X instead for Y', but the guidance is sufficient for a selectable tool.

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