> ## Documentation Index
> Fetch the complete documentation index at: https://schemabrain.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# find_relevant_tables

> Embedding-cosine semantic search over indexed column descriptions.

<Note>
  **Layer:** Physical schema
</Note>

Embedding-cosine retrieval over indexed column descriptions. Returns the
most relevant tables for a natural-language question, ranked by score.
Each hit names the matched column and surfaces its description.

```json theme={null}
{
  "qualified_name": "public.orders",
  "score": 0.79,
  "best_column": "user_id",
  "best_column_description": "Unique identifier linking each order to the customer who placed it",
  "token_estimate": 49
}
```

**Note on weak matches:** A low `score` (say, \< 0.85) is a *signal*, not an
error. The tool returned what semantic search found; the agent should judge
whether the score is strong enough to trust. See
[How retrieval works](/architecture#how-retrieval-works)
for why this design.