MCP server providing access to Example Corp company information, products, blog posts, industries, use cases, and contact methods
Solid foundation with consistent naming (verb_noun pattern), clear descriptions (avg ~80 chars), and proper JSON Schema with type constraints. All 8 tools have descriptions and input schemas. However, output schemas are not documented in the source, parameter descriptions lack depth (missing format/range guidance), and error handling is minimal. Tool composition is clean (single responsibility), but no pagination support visible for list tools despite potential large result sets.
Get a blog post by slug (returns full markdown body plus metadata).
Returns the standard company description and positioning.
Return ways to reach the organization (email, forms). Read-only — no programmatic submission.
Get full detail for a single product by id.
List the organization's published blog posts (metadata only, no body).
List the industries the organization builds platforms for.
List the organization's product portfolio. Optional status filter.
Output schemas not documented. LLMs cannot plan downstream tool calls or extract required fields without knowing response structure.
List tools (list_products, list_blog_posts, list_industries, list_use_cases) lack pagination parameters (limit, offset/cursor). Large result sets will blow context window.
Parameter descriptions are minimal (10-20 chars). Missing format guidance, constraints, and dependency hints. E.g., 'status' enum lacks explanation of when each lifecycle stage applies.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | 2026-07-28+ | v2 |
List the organization's documented product capabilities and use cases.
No error handling guidance visible. Tools should return actionable recovery hints (e.g., 'Product not found. Call list_products() to see available IDs').
Tool descriptions do not clarify when to use similar tools. E.g., get_company_info vs list_use_cases, what's the distinction? When should an LLM call each?