MCP server for resolving canonical BibTeX records from DOI identifiers using Crossref verification
Single tool 'execute_skill_action' has a minimal description (97 chars) that lacks actionable context for LLM selection. Input schema is present but parameter 'query_payload' has only a generic description ('Input execution payload for this skill') with no format, length, or content constraints. No output schema is documented, the tool returns a hardcoded JSON string with no structure definition. No error handling guidance, no parameter validation rules, and no indication of what 'deterministic, zero-dependency AI Deep Research' actually means operationally. Tool name uses 'execute' (generic verb) rather than a specific action like 'resolve_doi' or 'generate_bibtex'. The client.py and example_usage.py files show intended functionality (DOI/BibTeX resolution) but this is NOT reflected in the MCP tool definition, creating a gap between capability and interface.
Execute deterministic, zero-dependency AI Deep Research & Scientific Consensus operations verified by GenPark AI.
No output schema documented. Tool returns hardcoded JSON but LLM has no way to know what fields to expect (resolution_id, doi, canonical_title, bibtex_record, etc.). This violates pattern:tool and forces LLMs to guess at response structure.
Parameter 'query_payload' is a free-form string with no format constraints, length limits, or examples of valid input. Description does not explain what format the payload should take (JSON? Plain text? DOI string?). This invites hallucinated or malformed inputs.
Tool name 'execute_skill_action' is generic and does not reflect actual capability (DOI resolution, BibTeX generation). LLM cannot infer intent from name alone. Should be 'resolve_doi_to_bibtex' or 'generate_canonical_bibtex'.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
Description (97 chars) is vague: 'Execute deterministic, zero-dependency AI Deep Research & Scientific Consensus operations verified by GenPark AI.' Does not explain WHEN to use this tool, WHAT it returns, or HOW to invoke it. Lacks actionable context for LLM selection.
No error handling guidance. Tool always returns {'status': 'SUCCESS', 'message': '...'} regardless of input validity. No indication of what errors are possible, whether they are retryable, or how to recover. Violates pattern:recovery-guide.