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

No annotations are provided, so the description takes on the full burden. It discloses the algorithm: reads current average velocities, computes scale factors, and applies them in multiply mode, preserving original relative dynamics. It also notes that per-track velocity stats are returned before/after. This provides solid behavioral insight, though it does not explicitly state reversibility or edge-case handling (e.g., out-of-range targets), which keeps it from a 5.

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 comprehensive but well-organized with clear sections: overview, preset list, parameter definitions, return value, and examples. It is longer than average, but every section adds necessary detail for the tool's complexity. The front-loaded overview immediately conveys the core purpose, and the structured preset list is easy to scan. The lack of a brief parameter list for unit_index slightly affects structural completeness.

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?

The tool has 5 parameters and an output schema, and the description covers the key aspects: purpose, preset behavior, parameter formats, and return value (per-track stats). It includes practical examples for both preset and custom modes. The missing unit_index definition is the primary gap, and since the output schema exists, the description appropriately avoids re-explaining return structure. Overall, the description is complete enough for typical use, but the unit_index omission prevents a perfect score.

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 compensate. It thoroughly explains track_indices, preset (listing all preset options with target values), target_velocities (format and requirement to match count), and region_index (special values -1 and -2). The only gap is unit_index, which appears only in the example (as the first argument) without explicit explanation in the parameter list. This is a notable omission but the example infers its 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 and resource: 'Balance velocities across multiple tracks — MIDI mix leveling.' It clearly states the tool sets relative velocity levels across multiple note tracks. It also explicitly distinguishes itself from the sibling tool scale_velocity, which handles one track at a time, making the purpose unmistakable.

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?

Usage context is explicit: the tool is for balancing velocities across multiple tracks, with a direct comparison to scale_velocity ('Unlike scale_velocity (one track at a time)'). It also provides presets for specific musical genres/mix intentions, giving clear 'when to use' guidance. Examples further illustrate the intended call patterns.

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