Why it matters
Tool design determines agent capability. Good tools = capable agent; bad tools = broken agent.
Advertisement
The architecture
Schema: name, description, parameters (JSON Schema).
Descriptions drive LLM selection. Vague description → wrong tool used.
Advertisement
How it works end to end
Function calling: modern LLM APIs support structured tool calls directly. More reliable than text-parsing.
Description patterns: be specific about when to use, when not to use, what returns.
Errors: return structured errors so LLM can react.