get_notes

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

With no annotations provided, the description carries the full behavioral disclosure burden. It reveals key behaviors: note indices are ordered by onset and shift upon insert/delete/move, positions use a specific 'measure.beat' format with 1-based indexing, and 'phonemes' is conditionally present only for user overrides. This goes beyond a simple list and gives the agent critical expectations about the returned data's semantics and stability.

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 description is two sentences, tightly packed with essential information. The main purpose is front-loaded, and additional details are presented in a logical, readable order. Every sentence contributes useful context without redundancy or 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?

For a read-only list tool with no output schema, the description explains the return format (measure.beat, phonemes conditionality) and the order (by onset). It also flags the shifting note index behavior. However, it does not enumerate all fields of a note object (e.g., lyrics, onset, duration), so the agent must infer some return structure. Given the complexity of the tool and the absence of an output schema, this is a minor but notable gap.

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?

The schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds meaningful context: it explains the 'measure.beat' position format, the conditional 'phonemes' field, and references get_project_info for group semantics. This adds value beyond the raw schema, especially for understanding how fromMeasure/toMeasure relate to the position format, though it doesn't elaborate on every parameter.

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 opens with a specific verb+resource: 'List the notes of a track in the current Synthesizer V Studio project.' This clearly distinguishes the tool from siblings like get_phrases or get_phonemes by stating the exact object (notes) and scope (current project track). It also immediately establishes the context of the Synthesizer V Studio domain.

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 description provides practical usage guidance: it reminds the agent that track indices are 1-based and directs to get_project_info for reference. It also warns that note indices shift on edits, implying the tool should be re-read before making changes. However, it does not explicitly mention alternatives or when not to use the tool, which would have earned a 5.

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