スタイルを変える

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

With no annotations, the description carries the full burden and does so well: it discloses the mutation mechanism (build a partial .mss and bake it in), that a new version is produced rather than in-place mutation, and what is returned (pages/systems before and after). It also surfaces non-obvious interaction hazards (vertical-spread overrides, page width pairing) that no annotation or schema field would reveal.

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?

Front-loads purpose and example, then units, mechanism, and caveats in a compact block with no filler. Dense but every sentence contributes; the caveat sentence is slightly run-on but earns its space by preventing known failure modes.

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 mutation tool with no output schema and no annotations, it covers mechanism, units, validation, return contents, and interaction constraints — enough to call it correctly. Minor gaps remain: no guidance on discovering existing keys (style_get/style_list) or on failure behavior for invalid keys, but nothing essential is missing.

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 only 50% — `values` is an untyped object — but the description compensates by specifying the unit conventions per value type (SPATIUM in sp, page* in inches, spatium in mm, BOOL as true/false, POINT as {x,y}) and noting values are validated against type. The only parameter the schema documents (score_id) is already self-explanatory.

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: batch-setting style keys/values, illustrated with a concrete payload example ({"spatium":1.5, "minSystemDistance":10}). It is clearly the write counterpart to style_get, so an agent can distinguish it from the read sibling without inspecting either schema.

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?

Gives clear operating context: send only the keys you want changed, values are type-checked, and the tool bakes a fresh .mss via mscore -S to produce a new version. It adds two situational exclusions (enableVerticalSpread=true disables staffDistance/akkoladeDistance/minSystemDistance; pageWidth changes need pagePrintableWidth), though it never routes to sibling tools such as layout_set_stretch for non-style adjustments.

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