Analyzes (lints) a draft SMS/iMessage BEFORE you send it — it sends nothing itself, makes no delivery attempt, and has no side effects. Call this first, before send_message or any other messaging tool, on every outbound draft. Returns: a verdict (pass, warn, block, or needs_context — block-severity issues that depend on context you didn't provide, like whether this is the first message to this contact); a list of findings, each with a severity, a stable rule id, a plain-language explanation, an optional concrete fix, and a citation URL (AgentPhone docs, CTIA, or Twilio guidelines) backing the rule; and a send trace with the destination classification, the assumed delivery channel (imessage/sms/mms/unknown), SMS segment math (encoding, segment count), and — given a 10DLC campaign_type — a daily-quota illustration. Use it to catch carrier-filtering risks (missing opt-out language, missing brand identification, missing opt-in wording on first messages), invalid iMessage send_style values, oversized media carousels, and GSM-7/UCS-2 segment blowups from stray unicode before spending a real send. Every finding's fix field is directly actionable: apply it to the draft verbatim (e.g. append the exact quoted sentence), then call preflight_message again — loop until the verdict is pass. Never treat needs_context as permission to send; supply the missing context and re-check.