Tool Use

Tool use is an AI agent’s ability to call external functions, APIs, or systems — such as a search, a database query, or a payment — to act beyond generating text.

The model decides when to call a tool and with what arguments, then incorporates the result into its next step; this is what turns a language model into an agent.

Reliable tool use, including correct arguments and graceful handling of errors, is a major driver of real-world agent quality.