Compile a song spec into a FamiStudio project

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

Annotations already establish idempotent and non-destructive behavior, so the bar is lower. The description adds genuinely useful behavioral details beyond annotations: automatic filling of object ids, envelope masks and 256-slot pattern tables, plus the important pitch-offset gotcha about FamiStudio note names being one octave above standard pitch. This is valuable extra context with no contradiction.

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 information-dense and well-structured: a concise summary paragraph, two compact JSON examples, and a crucial octave-offset warning. Every sentence contributes something necessary, with no filler or redundancy.

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?

Given the very large nested schema and no output schema, the description covers the core knowledge an agent needs: what the input looks like, how the two note formats behave, what gets auto-filled, and how the returned object can be used downstream. It does not describe every optional field or error scenario, but those are partly represented in the schema and annotations, making this reasonably complete.

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?

With only 50% schema description coverage, the description compensates well by giving concrete absolute and grid examples, explaining the sustain behavior in grid form, and clarifying that outputPath is for writing a .fms file. The schema mostly lists types, so this interpretive guidance is necessary and useful. It does not enumerate every nested field, but the schema already provides structural detail for those.

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+object: 'Compile a compact JSON song specification ... into a complete FamiStudio project object', and clearly mentions the optional .fms output. It also distinguishes itself from sibling tools by stating the returned project can be passed directly to export_audio / verify_roundtrip / validate_fms, giving it a clear identity.

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 makes the use case explicit: when you have a compact JSON spec and want a FamiStudio project object or .fms file, use this tool. It also names downstream consumers of the result, which helps an agent plan a pipeline. However, it does not explicitly contrast with create_fms or state when not to use it, so it stops 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.