List non-system schemas in the gong-nl-db database. Call this first when exploring.

List tables and views in a schema. Use list_schemas first to find valid schema names. Defaults to 'public'.

Describe a table's columns, types, and nullability. Use this before writing a query against an unfamiliar table.

Return up to limit sample rows from a table (max 50). Useful for getting a feel for the data shape before running real analytical queries.

Run a read-only SQL query against gong-nl-db. Only SELECT, WITH (terminating in SELECT), and set-operation queries are allowed — any INSERT/UPDATE/DELETE/DDL is rejected before the query reaches the database. Results are capped at limit rows (max 1000).

Full-text search across transcript_segments. Prefer this over ILIKE when searching for phrases in calls — it uses the GIN FTS index and is ~100x faster. Returns matching segments joined to call metadata. query supports websearch syntax: "pricing objection", pricing OR discount, -competitor. since / until are ISO-8601 dates or timestamps (optional). host_email filters to calls owned by one user (optional).

Per-user daily call activity from the mv_user_daily materialized view — answers questions like 'how many calls did X have this week', 'avg talk ratio by person last month'. Filter by host_email (single user) or leave blank for team view. since/until are ISO-8601 dates (inclusive / exclusive). Returns one row per (host, date).

Semantic / meaning-based search across call transcript chunks using Vertex AI embeddings (text-embedding-005) and cosine similarity. Use this when the user asks to find calls 'about' a topic or concept — e.g. 'calls where pricing came up', 'conversations about churn risk', 'mentions of competitor X'. Unlike search_transcripts (FTS keyword matching), this finds conceptually related content even without exact word matches. since/until are ISO-8601 dates (optional). host_email filters to one rep's calls (optional). limit caps results 1–20 (default 10).

Return the Postgres query plan for a SELECT statement. Useful for debugging slow queries.