Tool selection
Tool selection is the process of determining whether a tool is needed and choosing an available tool suited to a task.
Build an AI Agent (From Scratch)
Tool selection is the process by which a language model determines whether a tool is needed and chooses the appropriate available tool.
- How it is used
- Uses tool calling to decide whether a request needs external execution or a direct answer.
- How deep it goes
- Traces selection from schemas through host execution and feedback, stopping short of broader selection algorithms.
- Examples
- Contrasts a South Korea capital question with a calculator call for multiplying 1234 by 5678.
- What you can do after
- Apply it via tool calling to define tools, execute selected functions, and return results through conversation history.
Read how Build an AI Agent (From Scratch) explains tool selection →
The Art of AI Product Development
Tool selection is the process by which an agent chooses an appropriate external tool for a task based on tool descriptions and the current request.
- How it is used
- Guides agents toward appropriate external capabilities while balancing simplicity, robustness, and functional power.
- How deep it goes
- Explains description-driven selection, missed or excessive use, tool-count limits, and write-access risks, without detailing model internals.
- Examples
- Uses PubMed, Yahoo Finance News, and YouTube Search to show domain, input, and output distinctions.
- What you can do after
- Diagnose/debug with it by refining descriptions when agents miss tools or invoke them unnecessarily.
Read how The Art of AI Product Development explains tool selection →
Also covered in
- Rearchitecting LLMsIn early access (MEAP)
- Data-Driven Cybersecurity
- Designing AI SystemsIn early access (MEAP)
- AI Model EvaluationIn 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.
- large language modelA large language model is a machine-learning model trained on extensive text data to process and generate natural language.
- retrieval-augmented generationRetrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- promptA prompt is text or other input supplied to an AI model to provide instructions, context, or other information that guides its response or generated output.
Related concepts
- Retrieverused by · A retriever is a software component that searches or queries an information source and returns items relevant to a query for use by downstream processes.
- semantic similarityuses · Semantic similarity is the degree to which two pieces of content or representations correspond in meaning, regardless of differences in wording or form.
- evaluationused by · Evaluation is the systematic assessment of a system, model, process, or outcome against relevant criteria or objectives using evidence.
- similarity searchuses · Similarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- AI agentuses · 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 selection
What is tool selection?
Tool selection is the process of determining whether a tool is needed and choosing an available tool suited to a task.
Which Manning books explain tool selection?
Build an AI Agent (From Scratch) and The Art of AI Product Development.
What should I know before learning tool selection?
Manning books that teach tool selection usually introduce language model, large language model, retrieval-augmented generation and prompt first.
What kinds of tool selection are there?
Kinds of tool selection include retrieval tool selection.
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.

