live_edit_notes

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

With no annotations at all, the description carries the full burden and does meaningful work: operations execute in order, results report what each op touched plus the notes afterwards, delete requires a filter, and quantize deliberately leaves Studio One's own quantize setting alone. It stops short of covering failure behavior, partial application, or permission/connection requirements.

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?

Front-loaded with the outcome first, then operations in execution order, then filters, return value, and undo. Every clause carries information, but the middle section is a dense run-on of shorthand notation (e.g. '1/8T (triplet)', '1/8. (dotted)') that would scan better as a list.

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 seven-operation batch mutation with no annotations and no output schema, the description supplies the essential missing pieces: operation ordering, per-op field semantics, filter semantics and defaults, beat reference frame tied to live_notes, return payload, and undo granularity. What remains absent, such as error/partial-failure handling, is minor relative to what is covered.

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 effectively 0% for the nested ops fields, and the description compensates strongly by mapping each op to its fields: transpose needs semitones, velocity takes set 1-127 or add, length takes set beats or scale, quantize takes grid formats plus strength 0-1, add takes a notes array. The only unexplained input is the top-level 'track' string — neither the schema nor the description says whether it is a name, index, or id.

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 — editing notes of an instrument track's parts in the running Studio One — and scopes it to the MCP Edit task that ships with the device. That verb+resource+scope combination separates it cleanly from sibling tools such as live_edit_events and live_notes.

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?

Gives concrete operational guidance: 'delete (needs a filter)', 'check with live_notes' before undoing, and 'one live_undo per operation, usually'. It routes the agent to live_notes for beat positions and live_undo for rollback, but never states explicitly when to prefer this over live_edit_events or what to do when a track isn't an instrument track.

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