write_drum_pattern

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

Annotations already flag destructiveHint=true, so the agent knows this mutates state, but the description never says what is destroyed — whether existing notes in the target clip are replaced or merged is the single most important unknown for this tool. It adds useful context about pad remapping and the style vocabulary, but omits idempotency/seed semantics and any prerequisite that a Drum Rack must already be loaded on the track.

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 purpose is front-loaded in the first clause and the remaining fragments are dense with concrete data (pad numbers, style names, remap example) rather than filler. The telegraphic sentence fragments are slightly clipped, but nothing is wasted.

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?

An output schema exists, so return values need not be described. But for a destructive, nine-parameter generator the description leaves key gaps: whether existing clip content is overwritten, what seed controls, and what bars/velocity/crash_first/fill_last_bar actually do. Adequate to invoke, not sufficient to invoke confidently.

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 coverage is 0%, so the description carries the burden and does partially discharge it: it enumerates the valid style values and explains the notes override format with a concrete example ({"crash": 48}), which the schema renders as an opaque object-of-integers. However, seven of nine parameters — bars, seed, velocity, crash_first, fill_last_bar, track_index, clip_index — receive no explanation at all, leaving the seed/reproducibility and track/clip targeting semantics undocumented.

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 names a specific verb and resource ("write a drum pattern for a Drum Rack") and scopes it to the GM pad layout, which clearly separates it from siblings like write_chords, write_melody, and write_bassline. It stops short of explicitly stating it is the drum-only generator, but the framing makes the domain 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 is implied rather than stated: an agent infers this is the tool for generating drum/percussion patterns on a Drum Rack. It does route the agent to get_drum_pads before remapping pads, which is a useful prerequisite pointer, but there is no explicit when-not guidance (e.g. use add_notes_to_clip for hand-authored MIDI, or move to a non-drums generator for pitched content).

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