Provider-specific requirements
Use autocomplete before structured CompanyDB or PersonDB searches when a field expects canonical values. Prefer in-DB search for broad list building and reserve realtime search/enrichment for freshness-sensitive cases. For job data, usecrustdata_v3_job_search for indexed job-listing discovery and crustdata_v2_live_job_search when the user explicitly needs current professional-network jobs for one known CrustData company id. Confirm the schema with deepline describe <tool-id>. V3 indexed search uses its own filter vocabulary, not a renamed V2 payload. Legacy dataset-table compatibility actions are hidden from discovery and should not be selected for new workflows.
Do not expose provider credit ladders to customers. Deepline tool pricing should remain Deepline-facing.
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.