live_notes

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

With no annotations supplied, the description carries the full burden and does disclose the critical traits: 'Read-only' and that unsaved edits are included, which tells the agent it reads live memory rather than persisted data. It also pins down unit conventions (MIDI pitch numbering with middle C = C3, velocity 0-127, seconds vs quarter-note beats), though it says nothing about truncation behavior or ordering of results.

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?

A single dense sentence that front-loads the resource and scope, then enumerates return fields with their units. No filler or repetition; the parenthetical about middle C = C3 is the only slightly heavy clause, but it prevents a real interpretation error.

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?

There is no output schema, and the description compensates well by enumerating the returned fields and their units. The remaining gaps are modest: no statement of result ordering or what happens when max_notes truncates the note list, and no error behavior for an unmatched track name.

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 100%, so the two parameters are already documented (exact track name, max_notes default 500). The description adds no meaning beyond the schema for either parameter — its detail is spent on return-value semantics instead — so the baseline of 3 applies.

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 resource and scope: MIDI notes inside an instrument track's parts, read from the running Studio One instance. An agent can distinguish it from mutating siblings like live_edit_notes, but the sibling is never named and the verb is implied by a noun phrase rather than stated outright.

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 'in the running Studio One, unsaved edits included' implicitly tells the agent to use this for live in-memory state rather than a saved song file (song_read). However, there is no explicit when-to-use/when-not guidance and no named alternative for editing notes or reading track structure.

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