A Failed Tool Still Produced a Success Claim

Failure-Transparent Agents fixes the failed observation and required evidence state before a model responds, separating post-failure reporting from tool choice and recovery. The benchmark contains 100 deterministic failure traces across five failure families, a neutral control and four user-pressure conditions. Across six models, three policies and 3,600 human-annotated responses, the authors report false-success rates of 22.8% under a baseline policy, 9.3% with a transparency instruction and 0.8% with a structured evidence contract. Fabricated-detail rates fell from 28.3% to 0.8% across the same endpoints while useful responses rose from 74.9% to 98.8%. This is a controlled blocked-task benchmark; it supports the tested reporting intervention, not a claim about all agents in open environments.