select

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

With no annotations, the description carries the full burden and does well: it discloses that no data is changed ('not the music'), that there is 'No undo step' (irreversibility), and that the piano roll auto-scrolls to the channel's notes. It omits return behavior and whether closing the piano roll preserves prior view state.

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 key scoping distinction is front-loaded in the first clause, followed by per-parameter behavior. Dense but every clause carries information; the parenthetical '(an id)' is slightly noisy but harmless.

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 3-optional-parameter, no-annotation, no-output-schema tool, the description covers purpose, side effects, irreversibility, and the piano roll interaction. The only real gap is semantics of omitted/null arguments, which an agent could plausibly need to decide whether to pass values at all.

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% — properties only have bare titles — so the description must compensate, and it does: it identifies `pattern` and `channel` as ids, and explains `piano_roll=True` opens while `False` closes. It does not say what a null/default value means for any of the three optional parameters.

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 states a concrete verb and resource: make `pattern` the current pattern, select `channel` in the channel rack, and optionally open the piano roll. The framing 'Change what the user sees, not the music' sharply bounds the scope and implicitly separates it from mutating siblings like set_pattern or set_channel, though no sibling is named explicitly.

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?

'Use it after writing notes so the user sees them' gives a clear trigger condition, and 'not the music' tells the agent this is a view-only operation rather than an edit. No explicit when-not guidance or named alternative is provided, which keeps it short of a 5.

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