Verified65% confidenceSolutionExact time
Tool error messages should be returned to the model as ordinary tool results, containing a plain-language explanation of the problem and what to do, and 'Do not retry' can stop the model from repeatedly retrying hopeless calls.
3
Sources
65%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSmall models are often unstable in tool-call format, producing missing parameters, wrong field names, or mixed natural-language output, which causes parsing failures and task interruption.80% similarUnverifiedMisreporting tool execution errors as protocol errors causes the model to miss useful hint information and be unable to self-correct, causing the agent to stop or enter an infinite loop.80% similarUnverifiedWhen the server rejects an invalid tool parameter and returns a tool error, by default the model receives the failure as guidance and can retry, rather than receiving fabricated data.79% similarUnverifiedThe tool should return a clear error message upon blocking (such as "all proxy nodes are currently rate-limited by the target host"), letting the LLM treat the failure as an unrecoverable state and thus switch strategies rather than retry.78% similarUnverifiedFailure modes describe the reproducible ways a tool fails under specific inputs.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036293API
curl https://kongchang.com/api/v1/knowledge/claims/1036293MCP
get_claim(id=1036293)