Definition
Tool calling is the mechanism by which an AI agent instructs a large language model to invoke an external function or API, allowing the agent to take actions and retrieve data beyond its training knowledge.
In Depth
When an LLM receives a user request it cannot fulfill from its training data alone, it generates a structured tool call specifying the function name and arguments. The agent runtime executes the call, returns the result, and the LLM incorporates it into its response. Search APIs are among the most common tools because they give agents access to real-time web information. Frameworks like LangChain, CrewAI, and the Anthropic SDK all support tool calling natively. Scavio provides pre-built tool definitions for these frameworks, so a search tool can be added to an agent in a single line of code.
Example Usage
A LangChain agent receives the question 'What is the cheapest flight to Tokyo next month?' and generates a tool call to Scavio's Google search API. The search results are returned to the LLM, which summarizes the best options for the user.
Platforms
AI Agent Tool Calling is relevant across the following platforms, all accessible through Scavio's unified API:
- Amazon
- YouTube
- Walmart
Related Terms
Function Calling (LLM)
Function calling is a capability of large language models that allows them to generate structured JSON outputs matching ...
Model Context Protocol (MCP)
Model Context Protocol (MCP) is an open standard that defines how large language models discover and invoke external too...
Agent Orchestration Framework
An agent orchestration framework is a software library that manages the lifecycle, communication, and tool usage of one ...