Tool result
The message a program sends back after running a tool the model asked for. Each result is a tool_result block that carries the id of the call it answers, the tool's output as text, and is_error when it failed. All the results for one turn go together in one user message, right after the model's reply, so the model can read what happened and decide what to do next.
Depth 1 · Foundation
You can write the tool_result blocks for a turn: one per tool call, each with the matching id, all in one user message after the model's reply, and a failure sent back as a result with is_error rather than raised.
Sign in to prove what you know with a short quiz, see how deep you've gone, and earn XP for it.
Sign in with GoogleDepths of understanding
- 1
Foundation
You can write the tool_result blocks for a turn: one per tool call, each with the matching id, all in one user message after the model's reply, and a failure sent back as a result with is_error rather than raised.
Your path here
What's still between you and Tool result, depth 1, in the order you can learn it.
- 1Language modelDepth 1 · Foundation · Language Models
- 2AI agentDepth 1 · Foundation · AI Agents
- 3TokenDepth 1 · Foundation · Language Models
- 4ProbabilityDepth 1 · Foundation · Probability
- 5Next-token predictionDepth 1 · Foundation · Language Models
- 6Stateless modelDepth 1 · Foundation · Language Models
- 7Context windowDepth 1 · Foundation · Language Models
- 8System promptDepth 1 · Foundation · Language Models
- 9Tool useDepth 1 · Foundation · AI Agents
- 10Tool resultDepth 1 · Foundation · AI Agents
Where it fits
Builds on
This concept