b612_designホームページ・LP・UI・チラシを作る前に必ず引く。生成AIが出しがちで顧客に「AIくさい」と言われる形（注記の左に色の縦棒・器と同じ色の面・均一な3列カード・全部同じ角丸と影）の禁止事項と、カードは角張らせる・並びの間隔は親のgapで持つ・複雑なSVGは無料素材を使う、などの必須事項を返す。あわせて、放っておくと生成AIが出さない6つ（斜めの帯・斜めの文字・派手なCTA・追従CTA・写真の上の文字・飾りの浮遊）と、そのまま貼れるCSS/JSの一覧を返す。snippet に名前を渡すとその実装を全文返す。
| Name | Required | Description | Default |
|---|---|---|---|
| snippet | No | 実装が欲しいときにファイル名（例 cta-shine.css / sticky-cta.js）。省略すると規約と一覧を返す |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it enumerates the returned content (禁止事項, 必須事項, 6つの不足パターン, 貼れるCSS/JS一覧) and the mode switch where supplying a snippet returns the full implementation. It does not state the operation is read-only or discuss freshness/staleness of the rules, but for a lookup tool the disclosure is substantial.
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 imperative trigger is front-loaded, followed by the returned categories and then the parameter behavior. It is dense and example-heavy (the parenthetical list of AI-like shapes), but each clause maps to real returned content rather than 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?
With one optional parameter, no annotations, and no output schema, the description must describe returns itself — and it does, listing the rule categories, the six missed patterns, and the snippet mode. An agent can call this correctly without further information; only the sibling-routing question remains open.
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 description coverage is 100% and the single parameter is already documented with format (file name examples) and the omit-behavior. The description's "snippet に名前を渡すとその実装を全文返す" restates the schema rather than adding new meaning, so the baseline 3 applies.
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 states a concrete verb (引く/返す) and a specific resource: design conventions for HP/LP/UI/チラシ, covering prohibitions, must-dos, AI-missed patterns, and CSS/JS snippets. It is clear what an agent gets back. It does not, however, differentiate itself from siblings like b612_rules, b612_principles, or b612_patterns, whose names suggest overlapping rule/principle content.
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?
"ホームページ・LP・UI・チラシを作る前に必ず引く" gives an explicit trigger condition, and the final sentence states when to pass a snippet name. No when-not conditions or named alternatives (e.g., b612_review_checklist) are given, so the routing between siblings is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.