Manuscript-anchored biblical doctrine engine. Provides 12 tools for lexical lookup, concordance walking, cross-references, variant inspection, parallel translation, versification resolution, cultural overlay, debate analysis, doctrinal verdicts, evidence inspection, historical attestation, and license auditing.
Server has 12 tools with basic descriptions but critical gaps in schema visibility and parameter documentation. Tool names follow verb_noun convention (lexical_lookup, concordance_walk, cross_ref) which is good. However, source code provided does not show actual parameter schemas, input/output type definitions, or detailed parameter descriptions for any tool. Only tool names and brief descriptions are visible. Without seeing the actual tool registration code (cd_mcp/tools/*.py files), schema quality cannot be verified. Descriptions are present but generic (10-50 chars), below the 50-200 char baseline for LLM-optimized descriptions. No evidence of error handling guidance, output schema documentation, or parameter constraints. All tools are READ_ONLY, which is appropriate for this domain, but this is not documented in tool descriptions.
Concordance walking tool for tracing word usage across scripture
Cross-reference tool for finding related verses
Cultural overlay tool for examining historical and cultural context
Debate analysis tool for examining theological interpretations of verses
Doctrinal verdict tool that returns the verdict, key verses, and diagnostics for doctrinal questions
Evidence inspection tool for examining pregenerated per-question evidence documents
Historical inspection tool for examining historical attestation and context
No input schemas visible in provided source. Cannot verify parameter types, constraints, or descriptions. All 12 tools score 0 on schema dimension.
Tool descriptions are generic and under 50 characters (baseline 50-200 for LLM optimization). E.g., 'Lexical lookup tool for biblical word analysis' (50 chars) lacks WHEN to use, WHAT it returns, and dependencies.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2026-07-28+ | v2 |
Lexical lookup tool for biblical word analysis
License audit tool for examining licensing information
Parallel translation tool for comparing multiple Bible translations
Manuscript variant inspection tool for examining textual variants
Versification resolution tool for mapping between different versification schemes
No parameter descriptions visible. LLMs cannot infer what 'verse', 'word', 'translation', or 'scheme' parameters mean without explicit documentation.
No output schema documentation. LLMs cannot plan downstream calls or extract structured data without knowing what fields are returned.
No error handling guidance visible. Tools do not document what errors can occur, whether they are retryable, or what the LLM should do next.