A modular React component framework and data dashboard platform with MCP server integration for component discovery and composition suggestions
Four tools with basic verb-noun naming (list_, search_, get_, suggest_). All have descriptions (10-20 chars baseline), but they are generic and lack LLM-optimization guidance. Input schemas are present with type declarations, but parameter descriptions are minimal (5-15 chars). No output schemas documented. No error handling guidance. No tool annotations (readOnlyHint). Composition is reasonable (single responsibility per tool), but descriptions do not explain WHEN to use each tool or what downstream actions they enable.
Get detailed information about a specific Blueprint Modular component by name
List Blueprint Modular components with optional category filtering and cursor-based pagination
Search Blueprint Modular components by query string with optional cursor-based pagination
Suggest a composition of Blueprint Modular components based on a user need description
Parameter descriptions are too brief (5-15 chars). 'Optional category filter for components' and 'Search query string' lack actionable detail. LLMs cannot infer valid formats, constraints, or examples.
No output schemas documented. Callers cannot know what fields to expect from list_components, search_components, get_component, or suggest_composition. This forces LLMs to guess downstream field names and risks broken tool chains.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All four tools are READ_ONLY but this is not declared in the MCP schema, forcing clients to infer safety from descriptions alone.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | 2026-07-28+ | v2 |
Tool descriptions lack WHEN-to-use guidance. 'List Blueprint Modular components...' does not explain when to call list_components vs search_components, or what the agent should do with the results.
No error handling guidance. If search_components returns no results or suggest_composition fails, the tool response does not tell the LLM what to do next (retry, refine query, ask user).