Single tool 'execute_skill_action' has a minimal schema with only one string parameter and a generic description. The tool name does not follow verb_noun convention (should be 'execute_skill' or similar). Description (104 chars) lacks specificity about what 'deterministic, zero-dependency AI Deep Research' actually does, when to call it, or what it returns. No output schema documented. The query_payload parameter has minimal description ('Input execution payload') and no format/constraint guidance. No error handling, no examples of valid payloads, no indication of what the tool actually returns beyond a generic success message. Tool definition is visible in code but implementation is a stub returning hardcoded JSON.

• Rename tool to 'resolve_doi_bibtex' or 'fetch_canonical_bibtex' to clearly signal the action and match the actual DOI/BibTeX resolver capability described in the repo name.
• Replace generic description with: 'Resolve a DOI to canonical BibTeX citation and Crossref metadata. Returns verified bibtex record, canonical title, and export URL. Call this to fetch citation data for a given DOI or research paper title.'
• Add format guidance to query_payload parameter: 'JSON string containing either {"doi": "10.xxxx/..."} or {"title": "..."} to resolve. Required: one of doi or title.'
• Document output schema in tool description or as a separate field: 'Returns {resolution_id, doi, canonical_title, bibtex_record, crossref_verified, schema_standard, bibtex_export_url}'.
• Add error handling: 'If DOI is invalid or not found in Crossref, return error with guidance: "DOI not found. Verify format is 10.xxxx/... and try a different DOI or search by title instead."'