Mehmet EmrahKonyaTR
← Back to glossary

Tool use

Araç kullanımı

D3

Tool use is an application pattern in which a model’s output is used to select or call a configured function or external capability and process its result.

Review status: 2026-11-26

Technical explanation

A system can process a model-produced function request, execute the selected configured function, and return the result as input for a later model step.

Conceptual boundaries

Tool use is not an autonomous agent by itself; the cited loop only establishes function selection, execution, and result return.

Provider-neutral example

A support system can process a model request for an account-lookup function, run the configured lookup, and give the returned status to the model.

Limitations

Tool-enabled systems add security and downstream-action risks, especially when model output can reach external systems or untrusted data sources.

Related concepts

Atomic claims and evidence

  1. 1.1NIST AI 100-2e2025, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
    Source
    NIST AI 100-2e2025, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
    Source role
    Authoritative source
    Exact locator
    Section 3.5 printed p. 54: model output, function call, and results returned in next prompt
    Supported claim
    NIST describes LLM-based agents as processing model output to select and call a function with specified inputs and returning results as part of a subsequent prompt.
    Last verification
    Review due
    Scope limitation
    This describes an agent tool-call loop and does not require every tool-enabled application to be an agent.
  2. 2.1NIST AI 100-2e2025, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
    Source
    NIST AI 100-2e2025, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
    Source role
    Authoritative source
    Exact locator
    Section 3.5 printed p. 54: tool-enabled agent security risks
    Supported claim
    When agents can take actions using tools, prompt-injection attacks can create risks such as arbitrary-code execution or data exfiltration.
    Last verification
    Review due
    Scope limitation
    This is a threat statement about vulnerable designs and does not establish that every tool call causes harm.