A tool index ranks on how well a description matches the request, which says nothing about whether the tool answers when it is called. Switch off 30% of the pool mid-run and an embedding retriever keeps sending 86.2% of selections to a tool that is down, because a dead tool is still the best semantic match. Keeping one success-or-error bit per tool, and letting it re-rank the top ten, takes that to 2.9% for 0.17 ms a call.