apply_drum_variation

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

Annotations are minimal (readOnlyHint=false, destructiveHint=false) and the description adds context beyond them: it discloses a 'guarded' mechanism implying expectedStateVersion checks, a deterministic seed, and promise of 'complete note readback' for verification. It does not contradict the annotations, and for a mutation-capable tool it appropriately signals that changes are controlled and observable. It stops short of detailing exact side effects or irreversible edits, but given the annotations carry little, the description adds meaningful behavioral context.

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 a single, front-loaded sentence that conveys the core action ('Plan or apply'), the guarded deterministic nature, and the two promised outcomes ('exact native context' and 'complete note readback'). There is no filler or repetition of schema data; every phrase earns its place, making it easy for an agent to parse quickly.

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 has 15 parameters, a nested fill object, and a plan/apply confirmation flow, the description is fairly terse. It does not explain the two-phase workflow or the relationship between dryRun, planHash, and confirmationToken, though the schema partly covers these. The promise of 'complete note readback' helps set output expectations, but the description alone leaves an agent uncertain about prerequisites and sequencing. Overall it is adequate but not fully complete for a tool of this complexity.

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 73%, which is moderate but not fully self-sufficient. The description itself provides no parameter-specific meaning, leaving parameters like bars, grid, and startBar without elaboration in either the description or schema. However, most critical parameters (dryRun, confirmationToken, expectedStateVersion, preserveAccentsAbove, etc.) do have schema descriptions that adequately explain their roles, so the tool remains usable without extra description-level parameter guidance.

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 a specific action ('Plan or apply') and a specific resource ('guarded deterministic drum variation'), and adds distinguishing qualifiers like 'exact native context' and 'complete note readback' that signal a careful, state-aware operation. However, it does not explicitly differentiate from sibling tools such as plan_drum_variation or humanize_midi_notes, so an agent might need to inspect the schema to see why this tool is unique.

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 phrase 'Plan or apply' implies a two-phase usage pattern (dry-run then confirm), and 'guarded' hints that it should be used when state integrity matters. Yet there is no explicit statement of when to choose this tool over alternatives, no mention of prerequisites (e.g., needing a prior plan or confirmation token), and no exclusion of cases where a simpler tool would suffice.

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