MCP server for AI-powered resume and career development tools including resume bullet writing, cover letter generation, LinkedIn profile optimization, and interview preparation
Server has 4 well-named tools with complete input schemas and descriptions. All tools follow verb_noun naming (write_*, optimize_*, prep_*). Schemas use Zod with proper types and descriptions for all parameters. However, output schemas are not formally documented, responses are inferred as text content only. Error handling is minimal; no recovery guidance or categorization. Parameter descriptions are adequate but lack format constraints and validation rules. No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite all tools being read-only operations.
Rewrite your LinkedIn headline, About section, and experience summaries to attract recruiters and the right opportunities.
Generate targeted interview prep: likely questions, strong answers using your background, and questions to ask the interviewer.
Write a tailored, compelling cover letter for a specific job application. Avoids generic templates that get ignored.
Transform weak job descriptions into powerful, metrics-driven resume bullet points that recruiters and ATS systems love.
Output schemas not documented. All tools return {content: [{type: 'text', text: string}]} but this structure is not declared in tool definitions. LLMs cannot plan downstream operations or validate response structure.
No tool annotations despite all tools being read-only. Missing readOnlyHint declarations prevent clients from optimizing caching and safety policies.
No error handling or recovery guidance. If Groq API fails, returns raw error without actionable next steps. LLM cannot determine if error is retryable or fatal.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 58 | 2026-07-28+ | v2 |
Parameter descriptions lack format constraints. E.g., 'years_experience' has min/max but description doesn't state the range. 'tone' enum is declared but description doesn't list valid values.
No pagination or result limits documented. Tools return unbounded text responses from LLM. If Groq returns 5000+ tokens, response could exhaust context window.