Skip to main content

COMPEL Glossary / tool-use-function-calling

Tool use / function calling

A prompt pattern authorizing the model to request named functions with structured arguments — searching the web, reading a database, calling a calculator, triggering an API — rather than generating all answers from its weights.

What this means in practice

Central to agentic applications; governance concerns include tool scope, parameter validation, and excessive agency.

Synonyms

function calling , tool-use prompting , external-tool invocation

See also

  • ReAct — An agentic prompt pattern interleaving reasoning steps (Thought) and action steps (Act — typically a tool call) over multiple turns, with observations from each action feeding the next reasoning step.
  • Structured output — Output formatted to match a declared schema — JSON with a JSON Schema, function-call arguments, or grammar-constrained text — rather than free text.
  • Excessive agency — A failure mode in which an LLM has been wired into tools and permissions whose blast radius exceeds what its supervision and validation logic can safely bound.
  • Agent-to-agent (A2A) protocol — The communication mechanism between AI agents — specifying message format, authentication, authorization scope, rate limiting, and audit logging.

Related articles in the Body of Knowledge