Tool Use and Function Calling: How to Give an LLM Tools Reliably

Learn to design tools (function calling) an LLM can use reliably: strict JSON schemas with enums and useful descriptions, the full agentic loop, parallel tool calls, argument validation with Pydantic, error handling the model can self-correct from, and the security practices you need before executing real actions. With production-ready code in Python and TypeScript. Expanded edition: Anthropic and Gemini APIs, tool_choice, structured output, argument streaming, timeouts and idempotency, context management, evals in CI, observability with OpenTelemetry, prompt injection, subagents, MCP, advanced patterns, a complete case study, and a production checklist. New expansion: human-in-the-loop and async approvals, multi-tenancy and identity (OAuth token exchange), scaling to hundreds of tools with dynamic selection, and programmatic tool calling.