Unverified50% confidenceFactExact time
When sending back a tool_result, it must carry the same tool_use_id as in the request; otherwise the model cannot determine which tool call the result corresponds to.
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe scope of forced tool calling (tool_choice) is a single generation (completion) rather than the entire session, so it must be re-specified on every call to the model.77% similarUnverifiedAfter receiving a request, the model may return a structured tool call rather than directly providing an answer.73% 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.73% similarUnverifiedEvery exposed tool consumes context Tokens on every request; information such as tool definitions, parameter descriptions, and return value formats all needs to be stuffed into the model context.71% similarUnverifiedThe default tool-calling path given on the Solon AI official website is user -> llm -> tool -> llm -> user; after setting returnDirect=true it becomes user -> llm -> tool -> user; what returnDirect changes is whether the tool result is handed back to the model for further processing—it is not a bypass of the model, nor a switch for approval, desensitization or idempotency.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092834API
curl https://kongchang.com/api/v1/knowledge/claims/1092834MCP
get_claim(id=1092834)