Tool chaining
Tool chaining is the sequential composition of multiple tool invocations, in which an earlier result informs or becomes input to a subsequent invocation.
AI Agents in Action, Second Edition
Tool chaining is the process in which the output of one tool call becomes the input to a subsequent tool call.
- How it is used
- Sequences dependent tool calls so agents can break down and complete multi-step goals.
- How deep it goes
- Defines dependent and parallel calls, demonstrates a research chain, and covers tracing, but defers advanced non-OpenAI API configuration.
- Examples
- Uses research-source lookup, travel booking, computer purchasing, and image creation to illustrate chained tasks and tools.
- What you can do after
- Diagnose/debug chains with OpenAI Traces and distinguish dependent sequences from parallel calls when designing agent workflows.
Read how AI Agents in Action, Second Edition explains tool chaining →
Software Testing with Generative AI
Tool chaining is a technique in which an agent passes the result of one tool invocation as input to a subsequent tool invocation.
- How it is used
- Coordinates database-oriented agent tasks by carrying outputs from one tool into another.
- How deep it goes
- Explains value retrieval, context passing, annotated parameters, and ordering guardrails, but does not guarantee model-selected execution order.
- Examples
- Demonstrates room creation, latest-room lookup, room-linked booking insertion, and database listing.
- What you can do after
- Apply it via annotated tool methods that return values and accept those values as parameters in later operations.
Read how Software Testing with Generative AI explains tool chaining →
AI Governance
Tool chaining is the composition of multiple tool operations into a sequence to achieve a task or produce an effect.
- How it is used
- Tests whether attackers can combine legitimate tools into harmful sequences during realistic, multi-step GenAI red-team exercises.
- How deep it goes
- Defines the attack pattern and places it in adversarial testing, but gives no concrete chains or implementation procedure.
- Examples
- Tests harmful sequences formed by combining legitimate tools, without specifying a particular tool sequence.
- What you can do after
- Evaluate agent exposure by testing whether legitimate tools can be combined into harmful sequences.
Introduction to Generative AI, Second Edition
A chained tool call is a sequence in which the result of one tool invocation informs a subsequent invocation.
- How it is used
- Uses repeated tool calls to complete tasks that a single invocation cannot solve.
- How deep it goes
- Explains the mechanism and a worked scenario, then flags intermediate-result tracking without detailing its implementation.
- Examples
- Uses spreadsheet reading, sales analysis, and web search to find a location’s current review rating.
- What you can do after
- Apply it via an agent architecture to answer questions requiring successive file, analysis, and web-search actions.
Read how Introduction to Generative AI, Second Edition explains tool chaining →
Also covered in
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.
Related concepts
- MCP tooluses · An MCP tool is an invocable operation or capability that a Model Context Protocol server exposes for clients to discover and call.
- trajectoryused by · A trajectory is an ordered record of states, actions, events, or operations showing how an agent or system progresses through an execution or process.
- tooluses · A software tool is a capability or utility that enables a person or system to perform a defined task or operation.
- tool useuses · 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.
- AI agentused by · An 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.
Questions about tool chaining
What is tool chaining?
Tool chaining is the sequential composition of multiple tool invocations, in which an earlier result informs or becomes input to a subsequent invocation.
Which Manning books explain tool chaining?
AI Agents in Action, Second Edition, Software Testing with Generative AI, AI Governance and Introduction to Generative AI, Second Edition.
What should I know before learning tool chaining?
Manning books that teach tool chaining usually introduce language model first.
What is the difference between tool chaining and parallel tool call?
Tool chaining is the sequential composition of multiple tool invocations, in which an earlier result informs or becomes input to a subsequent invocation. A parallel tool call is the concurrent invocation of multiple tools within a single model interaction.
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.



