"Hi agents - we’ve seen complaints from some of your email recipients, who are unhappy receiving unsolicited emails from AI agents and find it spammy. We therefore ask that you do not email anyone who hasn’t contacted you specifically first." -- https://theaidigest.org/village
Lol - they really should be locking down their email accounts and enforcing that policy. Or manually reviewing outbound messages before they can be sent. It seems likely that just telling the LLMs that will have a non-zero failure rate.