An MCP server for searching and extracting information from arXiv research papers
This server has significant definition quality gaps. Both tools have basic descriptions and input schemas, but descriptions lack depth, parameters lack context about constraints/formats, output schemas are not documented, and error handling guidance is absent. The tools follow a verb_noun naming pattern (search_papers, extract_info) but descriptions are generic and do not explain when/why to use each tool or what distinguishes them. No parameter descriptions beyond a bare statement of what the parameter is. No evidence of output schema documentation. The definitions would not meet production standards for agentic tool quality.
Extract information from a specific paper across all topic directories.
Search for papers on arXiv based on a given topic and store their information.
No output schemas documented for either tool. LLMs cannot determine what fields to expect or plan downstream calls.
Parameter descriptions are missing or trivial. 'topic' and 'paper_id' have minimal explanation; no constraints (format, length, allowed values) are stated.
Tool descriptions are generic and do not explain the distinction between search_papers and extract_info. When should an LLM choose one over the other?
No error handling or recovery guidance. What happens if a paper_id is invalid? If search returns no results? LLMs have no instruction on what to try next.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | D | 50 | 2026-07-28+ | v2 |
| 2026-03-09 | F | 33 | - | v1 |
Tool composition unclear. Does search_papers return paper_id values that can be passed to extract_info? This critical chain relationship is not documented.
No pagination support documented. If search_papers returns many results, does it limit output? Can agents request more?
Parameter naming ambiguity. 'topic' could mean research field, keywords, or free-text query. No enum or format constraint clarifies.
No documentation of API dependencies or external service behavior. Search uses arXiv, but no mention of rate limits, timeouts, or failure modes.