Fetch BibTeX records from the Google Scholar citation flow via CLI or MCP.
Single tool with clear naming (verb_noun: google_scholar_bibtex) and reasonable description (127 chars, within 10-1024 range). Input schema present with types and descriptions for all 3 parameters. However, output schema is NOT documented, the tool returns JSON text containing 'results' array with 'sourceType', 'origin', 'bibtex' fields, but this structure is only visible in stress-test assertions, not in the tool definition itself. Parameter descriptions are adequate but lack format/constraint details (e.g., what constitutes a valid 'query'?). No error handling guidance documented. Follows basic patterns but lacks production-grade polish.
Search Google Scholar for a paper title and return multiple BibTeX options from Scholar's citation export flow, ranked to prefer archival conference/journal records over preprints. Does not bypass CAPTCHA or access controls.
Output schema not documented. Tool returns JSON with 'results' array containing objects with 'sourceType', 'origin', 'bibtex' fields, but this structure is only visible in test code, not in tool definition. LLMs cannot plan downstream operations without knowing return structure.
Parameter descriptions lack actionable constraints. 'query' description says 'Paper title or Scholar search query' but does not specify format, length limits, or examples of valid queries. 'maxResults' has min/default but no guidance on performance implications of large values.
No error handling guidance. Tool description does not explain failure modes (e.g., CAPTCHA blocks, network timeouts, no results found) or recovery steps. LLMs cannot self-correct on failures.
STDIO transport only. Server is not remotely accessible and cannot be used by hosted MCP clients. Limits deployment scenarios significantly.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | 2026-07-28+ | v2 |