Skip to content

Tool Calling

Definition
AI-generated

Tool calling (also called function calling) is a pattern where the model emits structured requests—function name and JSON arguments—for a runtime to execute external code or APIs, then feeds results back for another model turn.

Topics
LLM and Agents
Synonyms
Function calling Tool use
Related
AI Agent Genome-Wide Association Study (GWAS) Large Language Model (LLM)

Why it matters in GWAS

Tool calling lets assistants run bcftools, query registries, or format plots—but mistakes in arguments can corrupt files or leak paths; allowlists, read-only modes, and logged tool traces are essential next to raw model fluency.

Example usage

"The reproducible workflow includes Tool Calling as a standard step in preprocessing and analysis."

AI Agent Genome-Wide Association Study (GWAS) Large Language Model (LLM) Model Context Protocol (MCP) Prompt
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Schick T, et al. (2023). Toolformer: language models can teach themselves to use tools. arXiv:2302.04761.
← Tokenization Top Variant →

Last updated (UTC · Git history)