レイアウトを調べる

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

With no annotations at all, the description carries the full burden and does disclose meaningful behavior: coordinates are in sp (staff-space) units, ids follow a concrete format (DYNAMIC#3, LYRICS#10, HAIRPIN#0.1) usable by element_offset, and it warns that the 1-based measure index can diverge from displayed measure numbers for pickup or skipped measures. It does not state read-only status explicitly or address cost/response size on large scores, so it is strong but not complete.

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?

One dense but well-ordered paragraph: return payload first, then units, then id format, then the measure-numbering caveat. Every clause carries operational information; nothing is redundant with the title or schema.

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 7-parameter, no-annotation, no-output-schema inspection tool, the description covers the returned structure (systems/pages, measures, symbols, overlaps), units, and id cross-references well enough to call it correctly. Remaining gaps are the unspecified include_measures behavior and no guidance on result size when include_elements is true.

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 57%, and the description compensates for the undocumented measure_from/measure_to by defining measures as 1-based sequential indices with the pickup/skipped-measure caveat. It also supplies the element-type id vocabulary that element_types filters on and the sp unit convention. It adds little for include_measures and does not clarify range semantics (inclusive/exclusive) for measure_from/to.

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 concrete enumeration of what the tool returns: measure order per system/page, per-measure width/stretch/break, symbol positions (dynamics, lyrics, text, hairpins) and overlap candidates. That is a specific resource (layout) with a read-oriented verb implied by '返す', so an agent knows what it gets back. It never explicitly contrasts itself with the sibling setters (layout_set_break, layout_set_stretch, layout_systems_every), which is the only reason it falls short of a 5.

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 only implied: it hands off element ids to element_offset and explains that measures[].index/no resolves numbering ambiguity, which tells the agent it is the inspection step before element_offset. There is no statement of when to call this versus the layout_set_* mutators, nor any prerequisite or exclusion. Adequate but inferential.

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