Track baseline service identity in search comparisons

When several MCP tools expose related search data, an earlier PostgreSQL prototype is not a baseline for an existing semantic service. Record the actual tool, backend mode, corpus, identity filter, query form and output budget for each measurement. A batched semantic question search and separate person-filtered lexical requests can both succeed while remaining incomparable as speed or recall tests. Label such runs functional spot checks. Verify shared source messages independently, assess displayed text diversity separately, and preserve source-reading costs rather than treating candidate latency as complete investigation time. Fallback-mode results also do not establish normal-backend performance.

Applies when: Multiple deployed or prototype retrieval paths are being compared through MCP. Keywords: MCP PostgreSQL search baseline prototype semantic lexical corpus scope benchmark