BM25S + PyStemmer-powered lexical retrieval (with stemming) and routing layer for LLM tools, documents, and hybrid RAG
Server has 7 tools with complete input schemas and descriptions. Naming follows verb_noun convention (retrieve_, build_, get_, update_, add_, delete_). Descriptions are present but brief (10-50 chars), below the 50-200 char LLM-optimized baseline. Parameter descriptions exist but lack detail on constraints, formats, and use cases. Output schemas are not documented. Error handling and recovery guidance are absent. No tool annotations (readOnlyHint/destructiveHint) despite clear risk classifications in metadata.
Add a new document
Build or rebuild BM25S index
Delete a document
Get all documents
Get current settings
Retrieve documents based on query
Update BM25S settings
Tool descriptions are too brief (10-50 chars). LLM-optimized descriptions should be 50-200 chars and answer WHAT, WHEN, and WHAT IT RETURNS. Current descriptions lack context for tool selection.
Output schemas are not documented. LLMs cannot plan downstream calls or extract required fields without knowing what each tool returns. No documentation of pagination, field types, or chaining IDs.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk classifications in metadata (READ_ONLY, WRITE, DESTRUCTIVE). Agents cannot determine which tools are safe to retry.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | 2026-07-28+ | v2 |
Parameter descriptions lack actionable constraints. E.g., 'temperature' has min/max in schema but description does not explain what values mean or when to adjust. 'ignore_zero' lacks explanation of its effect on results.
No error handling or recovery guidance. Tools lack descriptions of failure modes, retryability, or what the LLM should do if a call fails (e.g., 'index not found, call build_index first').