strum_midi_notes

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

The description goes beyond the annotations by stating a key behavioral constraint: 'Only onsets move; note lengths are preserved.' It also clarifies edge behavior for spread_beats=0 (no-op) and defines direction semantics. This aligns with destructiveHint=false and gives the agent confidence about side effects.

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 compact, front-loaded with the purpose, and every sentence adds value. The Args section is readable and parameter-specific, with no filler or redundant restatement of the tool name.

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?

For a tool with 12 parameters and no output schema, the description is incomplete: it does not explain how notes are selected (track_index, item_index, pitch_low, pitch_high, start_beat, end_beat, fields, channel), nor what return_notes does or what the tool returns. An agent would struggle to construct a correct call beyond the three described parameters.

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 description provides excellent meaning for spread_beats, direction, and chord_window_beats—the operation-specific parameters. However, schema description coverage is 0% and 9 of 12 parameters remain undocumented, including required parameters like track_index and item_index and the return_notes flag. The description partially compensates but does not cover the full invocation surface.

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: 'Strum chords' and explains the exact transformation ('stagger the onsets of simultaneous notes so each chord rolls out'). It clearly distinguishes this from sibling MIDI operations like transpose, humanize, or quantize by focusing on onset staggering while preserving lengths.

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 gives clear context for when to use the tool: when you want to strum chords by staggering onsets. It does not explicitly name alternatives or exclusion criteria, but the use case is unambiguous from the first sentence and the parameter semantics.

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