Provider-specific requirements
Use Snowflake when the task requires querying an organization’s warehouse data. Prefersnowflake_run_semantic_query when a saved semantic layer exists or the user asks for business metrics, dimensions, filters, funnels, or model-defined entities. The semantic query tool renders the stored Snowflake semantic layer into SQL and returns both rows and the rendered SQL for inspection.
Use snowflake_run_query only when the user provides raw SQL, asks for direct SQL, or the semantic layer does not cover the requested analysis. Leave write unset for read-only SELECT or WITH SQL. Set write: true only when the user intentionally wants a single statement that may modify or overwrite customer data. Never expose Snowflake warehouse spend as Deepline spend.
Find an applicable action
Confirm your effective workspace, then search the live catalog:Inspect the selected contract
Replace<returned-tool-id> with the identifier returned by discovery:
Prepare one reviewed input
Use one authorized record that matches the inspected schema. Preserve its source identity and define the result you will accept. Open the action reference for its payload and response shape. Provider-backed execution can incur usage or external effects. For reusable logic, follow Write Plays. For direct-call recovery, use Tool execution recovery.Continue only when the workspace, provider, required fields, acceptance rule, and applicable price are understood. Keep unavailable access separate from no-result evidence.