Each tool targets a distinct access pattern: search_notes returns ranked passages, read_note returns one full document by path, and list_notes gives an inventory with headings. The descriptions explicitly contrast them (e.g. 'use this instead of reading whole files'), leaving no plausible misselection.

All three tools follow a clean verb_noun pattern (search_notes, read_note, list_notes) with a consistent 'note(s)' object noun and lowercase snake_case throughout.

Three tools is on the lean end but each covers a genuinely distinct retrieval mode for a focused read-only notes server. No obvious bloat, though the surface is thin enough that one more lifecycle tool (e.g. index/refresh) would round it out.

List, search, and read form a coherent read-only browsing workflow with no dead ends for querying an indexed knowledge base. Minor gaps exist: there is no way to add/refresh indexed documents or inspect metadata such as timestamps, so the index itself must be managed elsewhere.