Verified65% confidenceFactExact time
stop_reason is a field in the Anthropic Claude API response, with common values including end_turn, max_tokens, and tool_use.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
8/24/2026
First Seen
Valid until: 11/22/2026
Sources
Related Entities
Related Claims
UnverifiedIn Claude's API, the stop reason is marked as tool_use when the model wants to call a tool.80% similarUnverifiedThe main loop translates stop_reason into the next action decision: tool_use enters the tool execution branch, max_tokens triggers max_output_tokens_escalate or max_output_tokens_recovery, and prompt_too_long maps to reactive_compact_retry.74% similarUnverifiedThe termination condition of an agentic loop typically falls into one of two categories: the model returns a plain-text response (stop_reason is end_turn), or the preset maximum number of iterations is reached.71% similarUnverifiedThe control flow rule of the agent loop is: as long as the stop reason is still tool use, keep looping; when the stop reason becomes end turn, stop and return plain text.71% similarUnverifiedAnthropic describes the client-side loop as a while loop based on stop reason: if the stop reason is tool_use, execute the tool and continue; exit upon encountering any other stop reason.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/795672API
curl https://kongchang.com/api/v1/knowledge/claims/795672MCP
get_claim(id=795672)