MCP server that provides a component library with tools to list and search UI components
Two tools with minimal definitions. list-components has empty input schema ({}), violating schema requirements. search-components has a single string parameter with description, but both tool descriptions are extremely brief (Japanese text, <30 chars when translated). No output schemas documented. No error handling guidance. No parameter constraints or validation hints. Tool names follow verb_noun pattern (list-, search-) but descriptions lack context on when to use each tool or what structure they return. No pagination, no result limits stated. Schemas present but incomplete, no output type definitions visible.
コンポーネント一覧を示します
コンポーネントを検索します
Empty input schema for list-components: {} provides no guidance on parameters or constraints. Tool descriptions are under 30 characters (Japanese: 'コンポーネント一覧を示します' ≈ 'Show component list'), violating the 10 - 1024 character baseline and providing no context on when to call this vs search-components.
No output schema documented for either tool. Callers cannot know what fields to expect (e.g., does search-components return component objects, IDs only, or a summary?). LLMs must guess the response structure, risking parsing errors and wasted tokens.
search-components accepts a free-form 'query' string with no constraints, format hints, or examples. No guidance on case sensitivity, partial matching, or field coverage (does it search name, description, props, or all?). LLMs may pass invalid or overly broad queries.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
No error handling or recovery guidance. If search-components finds no matches, the response is a plain string ('not found'), not a structured error. LLMs cannot distinguish success from failure or know what to do next (retry, refine query, list all components?).
Tool descriptions are in Japanese only, making them inaccessible to English-speaking LLMs and developers. Descriptions should be in English (or the primary language of the target audience) for maximum clarity and adoption.