Extract the settlement clause of a single Polymarket (.com or .us) or Kalshi market: who publishes the settling number (source), the clock time + timezone it is taken at (falling back to the market TITLE when the clause itself says "the time range specified in the title" — e.g. Polymarket's 15-minute Chainlink TWAP family), the precision of the computation (e.g. "1-minute candle close" vs "60-second trailing average" vs "twap_60s_lookback"/"twap_30s_lookback" vs "election outcome"), comparison_basis — what is compared to what (end_average_vs_start_average | close_vs_open; orthogonal to precision, since venues can share this comparison shape while computing each endpoint differently), the evidence standard (official_source | consensus_reporting | any_credible_report | unspecified), and void_handling (cancellation/postponement settlement — reused verbatim from bet_research's cancellation_rule detector, not re-derived). Parses Polymarket's description field (fetched via polymarket_market, or via polymarket_us_search for the .us venue) or Kalshi's rules_primary + rules_secondary fields (fetched via kalshi_market) with regex + a small vocabulary — no LLM pass, so an unusual clause reports confidence:"low" rather than a guess. Pass market as a Polymarket slug/URL (either venue) or a Kalshi market ticker (e.g. "KXBTCD-26SEP1317-T66999.99"); a Kalshi EVENT ticker (e.g. "KXBTCD-26SEP1317") also works — it picks one representative market under that event, since the settlement mechanism is normally shared across all strikes/legs in one event. Use this before treating a polymarket_kalshi_spread row as a real arbitrage: two ladders that look alike can settle on different sources (Polymarket.com's Chainlink TWAP stream vs Kalshi/Polymarket US's CF Benchmarks BRTI), at different times, or with a different lookback window — this tool is how you check. Pair with resolution_diff to compare two markets directly. KNOWN GAP: idiosyncratic phrasing that doesn't match the vocabulary returns confidence:"low" and evidence_standard:"unspecified" rather than an LLM-guessed answer.