Locate where a symbol is DEFINED, with its file:line, signature and doc.

This is the right first call for "where is X?" -- it is exact and ranked by structural importance, so if a repo has six functions called run, the one the codebase actually revolves around comes first.

Use search_code instead when you only know roughly what the thing does ("the retry logic") rather than what it is called.

Full-text search across symbol names, signatures and docstrings (BM25).

Use when you know the intent but not the identifier. Results are re-ranked by call-graph importance, so central symbols outrank incidental mentions.

Full detail for one symbol: signature, doc, members, callers and callees.

Prefer this over reading the whole file: you get the definition plus its immediate graph neighbourhood, which is usually all the context needed to make a safe edit. Set include_source=true when you intend to modify it.

Reverse call tree: everything that reaches this symbol, transitively.

The tool to use before changing a signature, tightening a validation, or deleting anything. Each edge reports the rule that produced it; treat sub-0.5 edges as leads rather than facts.

Forward call tree: what this symbol depends on, transitively.

Use it to understand an unfamiliar function without reading every file it touches, and to spot the layer a piece of code really sits in.

Impact analysis: what a change here could break, and which tests to run.

Combines the reverse import graph with the reverse call graph, then highlights test files specifically. Recall-first by design (confidence >=0.3): the expensive mistake is a missed impacted test, not an extra one.

Call this before editing shared code and after finishing, to pick tests.

"What else should I read before touching this?" via the call graph.

Runs personalized PageRank seeded on the anchor symbol and treats the call graph as undirected, so it surfaces collaborators a plain caller/callee list misses -- siblings that share a hub, helpers two hops away.

This is the structural analogue of semantic search, and it needs no embeddings: proximity in the call graph is the relationship.

Outline of one file: what it defines, what it imports, who imports it.

Cheaper than reading the file when you only need to know whether it is relevant, and it adds the reverse-import view that reading cannot give you.

Orient yourself in an unfamiliar repo: modules, layers, cycles, hotspots.

Start here. One call replaces a dozen exploratory file reads: you get module sizes and layering, import cycles, the highest-PageRank symbols (the risky ones to change) and the repo's entry points.

Index health: size, coverage, and the edge-resolution breakdown by rule.

Worth a call when graph answers look thin -- a low resolution rate or a stale indexed_at tells you the index needs rebuilding rather than the code being unusual.