tool loadout
The subset of tools offered to a model for one request, chosen for the task instead of offering every tool every time.
In more detail
Tool definitions are context too, and dozens of them cost thousands of tokens and confuse tool choice. Pick a loadout per request, or let the model search for tools and load only the ones it needs.
Related terms
- tool definition — The name, description and JSON Schema for its input that tell a model what a tool does and how to call it.
- context confusion — Irrelevant material in the context, such as unneeded tool definitions, lowering the quality of a model's choices.
- context engineering — Choosing and arranging everything a model reads on each call, from instructions and tools to history, memory and retrieved data, within a token budget.
Taught in
- From Prompts To Context — AI Engineering: LLM Apps, RAG & Agents
- When Context Fails — AI Engineering: LLM Apps, RAG & Agents
- Designing Tools A Model Can Use — AI Engineering: LLM Apps, RAG & Agents