tool result
The message your code sends back after running a tool call, matched to it by id, which the model reads before continuing.
In more detail
Return failures as results marked as errors, with a message the model can act on, rather than raising them. Keep results small and paginated, because they stay in the context for the rest of the conversation.
Related terms
- tool call — A model's structured request to run one tool with given arguments, returned instead of, or alongside, text.
- actionable error — An error message written for the model that says what failed and how to fix the call, so its retry can succeed.
- context editing — Removing stale content, such as old tool results, from a conversation's context before the next call.
Taught in
- From Prompts To Context — AI Engineering: LLM Apps, RAG & Agents
- Memory And Compaction — AI Engineering: LLM Apps, RAG & Agents
- Function Calling — AI Engineering: LLM Apps, RAG & Agents
- Designing Tools A Model Can Use — AI Engineering: LLM Apps, RAG & Agents
- The Agent Loop — AI Engineering: LLM Apps, RAG & Agents
- Planning, Memory And Many Agents — AI Engineering: LLM Apps, RAG & Agents
- Agent SDKs And Human Approval — AI Engineering: LLM Apps, RAG & Agents
- Connect An Agent To MCP — AI Engineering: LLM Apps, RAG & Agents
- Remote Servers And Trust — AI Engineering: LLM Apps, RAG & Agents
- Prompt Injection — AI Engineering: LLM Apps, RAG & Agents
- Evaluating RAG And Agents — AI Engineering: LLM Apps, RAG & Agents
- Capstone: The Tasks Assistant — AI Engineering: LLM Apps, RAG & Agents