add_voice

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

With no annotations present, the description carries the full disclosure burden; it does state the key behaviors that the voice shares the staff of `voice` and that a new voice id is returned. It omits whether the operation fails on the existing voice number, what happens to existing content, or any permission/state side effects, leaving meaningful gaps for a mutation tool.

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?

Two compact sentences with the core action front-loaded and parentheticals that each add real information (voice example, note-value syntax). Dense but not padded; no sentence is filler.

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?

No annotations, no output schema, and 0% schema coverage mean the description had to do heavy lifting, and while it does disclose the return value and the note syntax, four positioning parameters remain entirely undefined. For a 6-parameter creation tool with no structured documentation, this leaves the agent guessing on invocation details.

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 0% across 6 parameters, so the description must compensate and it only explains two of them: `voice` (staff anchoring) and `notes` (add_notes syntax, plain or single-dotted values). The bar, pos, beat, and flow parameters are documented nowhere, which is a substantial shortfall for a 6-param tool.

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 ('Start a new voice on the same staff as `voice`'), gives a concrete example use case (a second, stems-down voice), and names the follow-up tool (add_notes). It is clear what the tool does, though it does not explicitly contrast itself with add_notes as an alternative path.

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 through the workflow 'Returns the new voice id for later add_notes calls', which tells the agent this is a prerequisite step before typing notes into a second voice. There is no explicit when-not to use it or guidance on when a new voice is preferred over editing an existing one, so guidance is adequate but inferred.

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