liveBook · Manning

Tool selection

Tool selection is the process of deciding whether a tool is needed and choosing an available tool suited to a task.

How 2 Manning books explain it

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 →

Related concepts

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.