Tool and Function Calling
How LLMs request actions instead of taking them: schema design, tool-choice modes, parallel calls, error handling, and Anthropic vs OpenAI conventions
Deep dive on tool/function calling: the request-execute-return loop that turns a text generator into something that can act, why schema and description quality is the real bottleneck on tool-selection accuracy, tool-choice modes (auto/forced/none), parallel tool calls and their latency payoff, error handling and argument validation, where the permission boundary actually lives, keeping results compact, and a side-by-side of Anthropic tool use and OpenAI function calling.
Practice questions (9)
-
View →
Redesigning a Tool That Confuses the Model
Intermediate · Free -
View →
Choosing a Tool-Choice Mode for Structured Extraction
Intermediate -
View →
Parallel Tool Calls and a Latency Budget
Intermediate -
View →
What Happens When a Tool Call Fails
Intermediate -
View →
Where the Permission Boundary Actually Lives
Intermediate