← Back to Glossary
Tool Calling
Definition
Tool calling is the capability of an AI agent or language model to invoke external functions, APIs, or systems as part of its reasoning and execution process.
Purpose
The purpose of tool calling is to extend a model's capabilities beyond text generation by enabling it to perform actions, retrieve real-world data, and interact with external systems in a controlled manner.
Key Characteristics
- Explicit definition of available tools and their interfaces
- Structured invocation of tools based on model decisions
- Separation between reasoning and action execution
- Validation and constraint of tool inputs and outputs
- Controlled execution to prevent unauthorized or unsafe actions
Usage in Practice
In practice, tool calling is used to allow AI agents to query databases, call APIs, execute business logic, perform calculations, or trigger workflows as part of multi-step task execution.
One implementation of this concept is offered by Kenaz through the MCP Integration service.