[Scenario 6: Structured Data Extraction] You are building a structured data extraction system: pulling information from unstructured documents, validating output against JSON schemas, handling edge cases gracefully, and integrating with downstream systems.

You have several extraction tools — one per document type — and incoming documents of unknown type. The model must always produce a structured extraction, choosing the appropriate schema itself, and never reply with conversational text. Which tool_choice setting is correct?

Question

[Scenario 6: Structured Data Extraction] You are building a structured data extraction system: pulling information from unstructured documents, validating output against JSON schemas, handling edge cases gracefully, and integrating with downstream systems.

You have several extraction tools — one per document type — and incoming documents of unknown type. The model must always produce a structured extraction, choosing the appropriate schema itself, and never reply with conversational text. Which tool_choice setting is correct?

Accepted Answer

tool_choice: “any” — the model must call a tool but may choose which, guaranteeing structured output while leaving schema selection to the model

Answer

tool_choice: “auto” — the model decides whether to call a tool at all

Answer

tool_choice forced to one named tool, applied to every document

Answer

Omit tool_choice, since defaults handle this

Paper 3 · Question 52

Related Prompt Engineering & Structured Output questions