liveBook · Manning

Tool result

Also called tool output

A tool result is information returned by an external tool after it processes an invocation, potentially including output and execution status.

How 4 Manning books explain it

Build an AI Agent (From Scratch)

A tool result is the output produced by an external tool after processing an invocation and its arguments, including whether execution succeeded or failed.

How it is used
Represents tool execution outcomes and feeds them back into agent reasoning or execution traces.
How deep it goes
Defines fields, correlation, statuses, and event wrapping, but does not specify tool-specific result schemas.
Examples
Uses calculator multiplication, web search, Wikipedia search, and a multi-step distance-to-time calculation.
What you can do after
Operate agent loops that execute tools, correlate outputs, return results to models, and retain debugging traces.

Read how Build an AI Agent (From Scratch) explains tool result →

The Art of AI Product Development

Tool output is the data returned by an external tool after it processes an agent's request.

How it is used
Supports agent workflows by making tool-returned data usable by the language model.
How deep it goes
Explains verbose JSON trimming and relevant-field selection without specifying a particular parsing algorithm.
Examples
Uses verbose API JSON and selecting or trimming relevant fields as examples.
What you can do after
Apply it via custom logic or dynamic selection to reduce irrelevant tool-output information.

Read how The Art of AI Product Development explains tool result →

Designing AI Systems

A tool result is the structured output returned by an invoked tool and appended to the conversation for subsequent model reasoning.

How it is used
Carries tool outputs into subsequent agent-loop iterations for continued reasoning and action.
How deep it goes
Explains conversation-history integration, structured errors, multi-step use, and iteration limits without specifying a result schema.
Examples
Uses knowledge search, calendar creation, ticket creation, and calendar-conflict recovery as concrete tool-result scenarios.
What you can do after
Diagnose agent behavior by tracing tool outputs through conversation history and bounded reasoning iterations.

Read how Designing AI Systems explains tool result →

Context Engineering

A tool output is information returned by a tool after it runs, such as a response, computed value, or command result.

How it is used
Uses tool results to update an agent’s working context with information from external systems or computations.
How deep it goes
Defines results and traces their return to context, without detailing result validation or handling.
Examples
Uses a returned weather value and bug investigation involving an issue report, git diff, and project documentation.
What you can do after
Understand how a tool’s returned value becomes available to an agent during response generation.

Read how Context Engineering explains tool result →

Also covered in

What to know first

Related concepts

Questions about tool result

What is tool result?

A tool result is information returned by an external tool after it processes an invocation, potentially including output and execution status.

Which Manning books explain tool result?

Build an AI Agent (From Scratch), The Art of AI Product Development, Designing AI Systems and Context Engineering.

What should I know before learning tool result?

Manning books that teach tool result usually introduce AI agent, context window and Python first.

What is tool result part of?

Tool result is part of working context. Working context is the information and intermediate state available to an AI model or agent while performing a task that can influence its behavior.

What is tool result also called?

Tool result is also called tool output.

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.