A Spring Boot-based MCP server that provides tools for querying person data by ID and nationality
Two tools with minimal descriptions (10-12 chars each, well below 20-char floor) and basic parameter documentation. Tool names follow verb_noun convention (getPersonById, getPersonsByNationality) but descriptions lack context on WHEN to use each tool, what they return, or dependencies. Input schemas present but sparse: only type and description, no constraints, enums, or validation guidance. No output schema documented. No error handling guidance. No pagination support despite getPersonsByNationality returning a list. Follows basic Spring AI annotation patterns but lacks production-grade LLM-optimization.
Find person by ID
Find all persons by nationality
Descriptions critically short (10-12 chars). 'Find person by ID' and 'Find all persons by nationality' fall below 20-char floor and lack context on when to use, what to return, or prerequisites.
No output schema documented. LLMs cannot plan downstream calls or extract fields without knowing the response structure (Person object fields, List structure, pagination).
getPersonsByNationality returns a list but lacks pagination (limit, offset, page_size, total_count). Large result sets will blow context window and degrade LLM reasoning.
No error handling guidance. If person not found or nationality invalid, LLM receives null/empty with no recovery hint (e.g., 'Try search_persons() with partial name').
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | <=2025-11-25 | v2 |
Parameter 'nationality' accepts free-form string with no enum, format, or validation constraint. LLM may hallucinate invalid values; no guidance on valid options.