Tool "scan_content" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.
scan_content · field annotations{}
This is an automated, point-in-time report from passive metadata analysis (the server's own initialize and tools/list advertisement). No tools were invoked. The grade reflects deterministic checks only; findings marked "llm" are triage signals for human review and do not affect the grade. Verify any finding with its reproduce command. Rulepack rulepack-2026.08.1.