Unverified50% confidenceFactExact time
The Anthropic Claude API requires tool results to be placed in a user message immediately following the model's request, with one result per request, and the result must come first in that message.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedThe workflow of the lead follow-up blueprint is: a customer completing a form triggers the process, an AI model drafts the reply content, and then the reply is saved as a draft via the Gmail interface.71% similarUnverifiedTool Calling allows an LLM to decide, during response generation, to invoke predefined external functions or APIs and incorporate the results into subsequent reasoning.71% similarVerifiedAfter the client receives the tool execution result, it needs to construct a message with the role set to tool, carrying the corresponding tool_call_id and execution result to send back to the model.71% similarUnverifiedThe way the Decisions API works is that a developer passes in a piece of text or an image, sets a question along with a set of possible answers, and the model returns the selected result.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1043364API
curl https://kongchang.com/api/v1/knowledge/claims/1043364MCP
get_claim(id=1043364)