Tool execution
Tool execution is the process of invoking a tool, function, API, or service to perform an operation and obtaining its result.
Build an AI Agent (From Scratch)
Tool execution is the process of sending a tool request with arguments to a server, running the tool, and returning its result.
- How it is used
- Enables agents to act on tool requests and return external results for further reasoning.
- How deep it goes
- Works through schemas, function dispatch, result messages, and a repeated agent loop, then introduces standardized MCP execution.
- Examples
- Uses a calculator call and a web-search agent answering a question about a recent Nobel Prize.
- What you can do after
- Builds it from scratch using a function registry, argument parsing, and a conversation loop.
Read how Build an AI Agent (From Scratch) explains tool execution →
Designing AI Systems
Tool execution is the invocation of an externally defined function, API, or service on behalf of an AI application.
- How it is used
- Enables AI applications to invoke external systems while centralizing discovery, validation, credentials, and execution management.
- How deep it goes
- Defines a managed gRPC contract and execution flow, but defers detailed implementation of external integrations and safety policies.
- Examples
- Uses appointment scheduling, intake submission, insurance verification, availability checks, and a Tool Service gRPC contract.
- What you can do after
- Operate tool integrations through discovery, pre-flight validation, synchronous or asynchronous execution, and managed credential injection.
Also covered in
- AI Agents and Applications
- Designing AI AgentsIn early access (MEAP)
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- schemaA data schema is a formal specification of the structure, fields, types, relationships, and constraints of data.
Related concepts
- tool useused by · Tool use is the capability of an AI system or agent to request external software operations through defined interfaces to obtain information or perform actions.
- toolboxused by · A toolbox is a registry or mapping of named tools, typically including callable functions and their configurations.
- functionuses · A function is a callable unit of program code that performs a computation or operation, can accept inputs, and may produce a result or side effect.
- contextproduces · Context is the relevant information, state, or circumstances surrounding an input, decision, or activity that influence its interpretation or behavior.
Questions about tool execution
What is tool execution?
Tool execution is the process of invoking a tool, function, API, or service to perform an operation and obtaining its result.
Which Manning books explain tool execution?
Build an AI Agent (From Scratch) and Designing AI Systems.
What should I know before learning tool execution?
Manning books that teach tool execution usually introduce language model and schema first.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

