A resume and job description parsing API built with Hono that extracts structured data including skills, experience, education, contact information, and language proficiency from resume and job description text.
Three tools with clear verb-noun naming (parseResume, parseJobDescription, matchResumeToJob) and reasonable descriptions (100-150 chars). All tools have input schemas with type definitions and parameter descriptions. However, output schemas are not documented, LLMs cannot predict what fields to expect from responses. Parameter descriptions are minimal (10-20 chars) and lack format/constraint details. No error handling guidance. Tools lack idempotency hints and confirmation patterns despite being read-only. Missing tool annotations (readOnlyHint present in metadata but not in schema).
Compares a resume against a job description and returns a match score with detailed analysis of skill matches, experience fit, and recommendations.
Parses job description text and extracts structured data including required and preferred skills, experience level, and job metadata.
Parses resume text and extracts structured data including contact information, experience, education, skills, languages, and metadata about the resume.
Output schemas not documented. LLMs cannot predict response structure (fields, types, nesting). Forces agents to guess what data is available for downstream reasoning.
Parameter descriptions are too brief (10-20 chars). 'The resume text content to parse (minimum 10 characters)' lacks guidance on expected format, length limits, or what 'structured data' includes. LLMs need richer context for selection.
No error handling guidance. If parsing fails (malformed input, too short, unsupported format), tools provide no recovery hints. LLMs cannot self-correct or guide users.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 48 | 2026-07-28+ | v2 |
Tool annotations missing from schema. Risk metadata (READ_ONLY) is in tool metadata but not in input schema as readOnlyHint. Clients cannot discover tool safety properties from schema alone.
No result limits or pagination guidance. If parsing returns large structured objects (e.g., 100+ skills, 50+ experiences), response could bloat context. No mention of truncation or pagination strategy.