Unverified50% confidenceDecision RuleExact time
Tool output should return only what the model needs for its next decision, use human-readable values rather than raw nested data, and list-type tools should return a summary and state any truncation.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedObservability platforms should not conflate "model output" with "tool return results": read-only tools should return consistent data for the same input and are a reliable anchor for verifying system correctness, whereas model output is inherently uncertain.72% similarUnverifiedTool 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.72% similarUnverifiedIn the reporting Agent, passing dataset IDs between tools instead of having the LLM recite raw records line by line saves tokens and reduces errors.72% similarUnverifiedWhen model output does not conform to the expected schema, the workflow should route that record to a manual review queue rather than silently falling back to default values.69% similarUnverifiedTo track and reproduce failures, each evaluation case needs to record the question, expected answer, retrieved document IDs and chunks, similarity scores, prompt and model configuration, generated answer, metric results, latency, and token usage, while avoiding recording keys or sensitive user data.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036292API
curl https://kongchang.com/api/v1/knowledge/claims/1036292MCP
get_claim(id=1036292)