記号をずらす

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 for the key behaviors: relative vs absolute semantics, the default mode, the y-axis direction (downward positive), and the critical autoplace=false meaning (MuseScore stops auto-repositioning). It omits auth needs, reversibility, and return behavior, hence not a 5.

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-loaded with purpose, then targeting, then modes, then autoplace — a logical progression where each sentence conveys operational detail. Dense but not padded; minor density in the targeting clause keeps it from a 5.

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 10-param mutation tool with no annotations and no output schema, the description covers targeting, mode semantics, and autoplace behavior adequately. Gaps remain around return values and whether multiple elements can be affected, but the essentials for correct invocation are present.

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 40% across 10 params, but the description compensates well: it defines id format (DYNAMIC#3), the type+measure+staff+nth targeting, dx/dy units (sp, y-down), mode defaults, and autoplace. Most semantically ambiguous params gain meaning beyond the schema, though score_id and the nth detail rely on schema text.

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 (ずらす/move) plus the resource (記号), and enumerates concrete element types (強弱・歌詞・テキスト・テンポ・ヘアピン). An agent can distinguish this from layout_inspect and layout_set_* siblings without opening the 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?

Explains the two targeting strategies (layout_inspect element id vs type+measure+staff+nth) and the two operating modes (relative default vs absolute), giving clear when/how context. It does not, however, explicitly name sibling alternatives or exclusions, 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.