Tool Registry
A centralized catalog of available tools, their schemas, descriptions, and access policies that agents can discover and invoke at runtime. A tool registry decouples tool definitions from agent code, enabling dynamic tool management.
A tool registry acts as a service directory for agent capabilities. Instead of hardcoding tool definitions in each agent, you maintain a central registry where tools are registered with their schemas, descriptions, authentication requirements, and usage policies. Agents query the registry to discover available tools based on their current task context.
For organizations with multiple agent systems, a tool registry prevents duplication, ensures consistency, and simplifies governance. When you update a tool's API, you update it once in the registry rather than across every agent that uses it. Access control policies are centralized, making it easier to audit which agents can perform which actions. The registry also enables dynamic tool selection: an agent can discover relevant tools at runtime based on the user's request rather than being limited to a static set. This becomes increasingly important as your tool ecosystem grows beyond what fits in a single model's context window.
Related Terms
Model Context Protocol (MCP)
An open standard that defines how AI models connect to external tools, data sources, and services through a unified interface. MCP enables agents to dynamically discover and invoke capabilities without hardcoded integrations.
Tool Use
The ability of an AI model to invoke external functions, APIs, or services during a conversation to perform actions beyond text generation. Tool use transforms language models from passive responders into active problem solvers.
Function Calling
A model capability where the AI generates structured JSON arguments for predefined functions rather than free-form text. Function calling provides a reliable bridge between natural language understanding and programmatic execution.
Agentic Workflow
A multi-step process where an AI agent autonomously plans, executes, and iterates on tasks using tools, reasoning, and feedback loops. Agentic workflows go beyond single-turn interactions to accomplish complex goals.
ReAct Pattern
An agent architecture that interleaves Reasoning and Acting steps, where the model thinks about what to do next, takes an action, observes the result, and repeats. ReAct combines chain-of-thought reasoning with tool use in a unified loop.
Chain of Thought
A prompting technique that instructs the model to break down complex problems into sequential reasoning steps before producing a final answer. Chain of thought significantly improves accuracy on math, logic, and multi-step tasks.