Each tool has a clearly distinct purpose: biji_search returns AI-generated answers with citations, biji_recall returns raw content snippets ranked by relevance, and biji_list_kb lists configured knowledge bases. There is no overlap between these operations, so an agent can confidently choose the right tool based on whether it needs processed or raw results.

All tool names follow the biji_ prefix and a simple verb pattern: search, recall, list_kb. This is consistent and predictable. The only minor deviation is that list_kb uses an underscore while the others are single verbs, but the overall convention is uniform.

With 3 tools, the server is well-scoped for a knowledge base search service. Each tool serves a distinct need—AI search, raw recall, and KB discovery—without unnecessary extras. This is within the ideal 3-15 range and feels complete for its niche purpose.

The server covers the core functionality of searching and recalling knowledge base content, plus listing available KBs. A minor gap is the lack of a tool to retrieve metadata or browse specific documents within a KB, but that is beyond the primary search/recall workflow and can be worked around.