Use at the start of a session, or when unsure if search results might be stale. Reports whether a codebase is indexed, index size/engine availability, memory usage, and a stale/staleness_warning pair if files changed since the last index (a background reindex is auto-triggered).

Use for liveness/readiness probes only (uptime, which engines are up) — not for checking whether the index is fresh or complete; use status for that.

Use first on any new or changed codebase, before any other tool — everything except status/health requires an index. Supports comma-separated paths for multi-folder/monorepo indexing (processed sequentially to keep RAM low). Incremental by default once an index exists, and reports live progress instead of blocking silently. After this completes, a file watcher keeps the index fresh automatically (NEXUS_AUTO_WATCH) — re-running index manually is rarely needed.

Use for any "where is/how does/find" code question — preferred over Grep/Glob, and usually answerable from the returned code_snippet without a follow-up Read. Falls back to live grep automatically when hybrid results are sparse. Returns a non-null warning if the index looked stale (a background reindex is triggered; results still return now).

Use to look up a specific function/class/symbol by name — preferred over Grep since it returns the definition plus its call-graph relationships in one call. Set exact=False for fuzzy substring matching when unsure of the exact name.

Use to trace who calls a function (direction='callers'), what it calls (direction='callees'), or — with transitive=True — the full transitive blast radius of changing it. MUST use transitive=True before refactoring or editing a widely-shared symbol; grep can't show transitive impact.

Use for code review or quality assessment — cyclomatic/cognitive complexity, dependency analysis, code smells (long/complex functions, large classes, dead code), and an overall quality score. Optionally scope to a subdirectory or file via path.

Use for onboarding to an unfamiliar symbol — combines its call-graph relationships, related code found via semantic search, and quality metrics in one call, so Read is often unnecessary. Use verbosity='summary' for a quick look, 'full' when you need everything.

PREFERRED over Glob/ls/manual browsing for project understanding. Use 'summary' for a quick project orientation, 'architecture' for design/dependency structure, 'full' for both in one call.

Persist and retrieve project context across sessions. Use action='store' to save a decision/note, action='search' to find memories by semantic similarity, action='delete' to clean up by ID, tags, or type.