What is Tool Calling?

Summary

Tool calling lets an AI model interact with external tools, APIs, and systems to retrieve information or perform actions beyond its training data, turning a conversational model into an agent that can act. The process is an application-mediated loop: the model recognizes when outside help is needed, selects a tool from schema-described options, emits a structured request—typically JSON—and receives the result as context for its response or next step. Available tools can support information retrieval, code execution, process automation, and smart-device or IoT monitoring, while complex tasks may chain multiple calls into a workflow. The piece also distinguishes tool calling from function calling, describing the latter as a subset, and presents MCP as a standardization layer for describing, discovering, and invoking tools, with Databricks Agent Bricks offering governed integrations and agent-development support.

Context

Language models are limited to generating text from their training data unless they can access external systems. AI agents need a way to retrieve live information, execute code, and trigger actions in order to complete real-world, multi-step tasks.

Approach / What changed

The model identifies when a tool is needed, chooses from schema-described tools, and generates a structured request for an application layer to execute. The returned result is supplied back to the model, which can answer, confirm an action, or continue with additional tool calls. MCP provides a standardized layer for describing, discovering, and invoking tools.

Takeaways

• The model does not execute tools directly; it generates a structured request, typically JSON, and an application layer fulfills it.
• Tool calling supports retrieval, code execution, process automation, and smart-device or IoT integrations, including multi-step workflows that chain calls.
• Function calling is described as a subset of tool calling, while MCP standardizes how tools are described, discovered, and invoked.

Related reading