Tool result
A tool result is information returned by an external tool after it processes an invocation, potentially including output and execution status.
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.
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.
Also covered in
What to know first
- AI agentAn AI agent is a computational system that uses artificial intelligence to interpret information and select or perform actions toward goals while interacting with an environment.
- context windowA context window is a bounded span of sequence elements or contextual information that a model or processing operation can consider together.
- PythonPython is a high-level, general-purpose, dynamically typed programming language with readable syntax and support for multiple programming paradigms.
Related concepts
- working contextpart of · Working context is the information and intermediate state available to an AI model or agent while performing a task that can influence its behavior.
- tool useproduced 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.
- code executionproduced by · Code execution is the process by which a computing system runs program instructions to produce results or effects.
- contextpart of · Context is the relevant information, state, or circumstances surrounding an input, decision, or activity that influence its interpretation or behavior.
- memoryproduces · Memory is a storage capability or mechanism for retaining information or computational state for later access or use.
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.



