Tool Use & Function-Calling Design Patterns
Every dated snapshot of this topic, newest first. Each snapshot is frozen as of its date; links and versions reflect what was true then.
Tool Use & Function-Calling Design Patterns for AI Agents — Best Practices (as of 09 Aug 2026)
How to design, call, and secure tools/functions across Anthropic Claude, OpenAI, and vendor-neutral (MCP/framework) patterns: schema design, tool_choice/strict modes, parallel calls, error handling, and the injection/sandboxing risks that come with letting a model execute real actions.