A practical recipe for getting tool calling right, from designing schemas to choosing a model, with every step linked to the in-depth docs on toolaugmented.ai.
Six steps for shipping reliable tool calling. Try each one in the workspace as you go.
How the model, your tools and the tool-result turn fit together.
Names, descriptions, types, enums and distractor tools that models get right.
Paste them in the Tools editorPolicies, defaults and scope: when to call, when to ask, when to answer directly.
Return success, errors, timeouts and large results in a way the model can use.
Add a Tool result turnSingle, parallel, sequential and no-call cases, plus the tricky ones.
Try them in the ArenaMetrics and per-slice evaluation on held-out tools, before you commit to a model.
Compare models blindThe fundamentals of function calling across providers.
Concrete rules for schemas, prompts and tool results.
Build training data that teaches a model to call tools well.
Measure before you ship.
Look things up.
Guides are hosted on toolaugmented.ai, our open documentation on tool-augmented AI.