transform_notes

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the mutation/idempotency profile is covered. The description adds one genuinely useful trait beyond that — note IDs are preserved ('ids kept') — but says nothing about undo/reversibility, permission needs, or what happens to notes not matched by the filter.

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?

Purpose and filter default are front-loaded in the first sentence, then a consistent 'operation: options' block. The trailing semicolon-joined line ('legato; reverse ...; stretch ...; shift ...') is dense but still readable, and nothing is wasted given the parameter count.

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 22-param mutation tool with no output schema and zero schema coverage, the description is unusually complete on operation semantics. It still leaves the filter parameters to be looked up in get_notes and gives no hint about the return value or error behavior, so an agent must go elsewhere for those.

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?

With 22 parameters and 0% schema description coverage, the description does the heavy lifting, mapping most options to operations (semitones/steps, grid/amount/swing, timing/velocity/seed, factor/offset/value/random, start/end/loop for reverse and stretch). It leaves ~7 params (track, slot, arrangement_clip, note_ids, pitches, pitch_min/max) covered only by the 'filters as in get_notes' reference, which pushes the agent into another tool's schema.

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?

States a specific verb and resource ('Transform notes') plus the crucial scope detail 'in place (ids kept)', which separates it from write_notes (rewrites) and delete_notes. It also cross-references the get_notes sibling for the filter semantics, so an agent can place it in the note-editing family without opening a schema.

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 operation list effectively says which operation to pick for a desired effect (transpose for pitch, quantize for grid, humanize for feel), and the 'default: all' note clarifies filter behavior. However, it never says when to use this tool versus edit_notes or write_notes, so alternative selection is left to inference.

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