Ruling — Magic: The Gathering

You asked

How do I set up the game?

Answered counted as answered

To set up the game, follow these steps: 1. Obtain your own Magic deck [1]. 2. Ensure you have a way to keep track of both players' life totals and small items to use as counters or tokens [1]. 3. Find an opponent who will play against you using his or her own deck [1]. 4. Decide which player will go first; if you just played the same opponent, the loser of the last game decides, otherwise roll a die or flip a coin to decide [1]. 5. Each player shuffles his or her deck [1]. 6. Each player draws a hand of seven cards to start [1]. 7. If you do not like your opening hand, you may mulligan by shuffling your hand back into your deck and drawing a new hand of six cards (you can continue this process, drawing one fewer card each time, until you decide to keep your cards) [1].

[1] RULEBOOK Magic: The Gathering — Rulebook · p.16 · Section 3: Playing a Game

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 241 ms · ask 10152 ms · total 10404 ms
single-flight (PR-5): queued 0 ms · generation 10404 ms
retrieval refs (raw): [{"page": 15, "score": 0.030214, "snippet": "When a Magic card contradicts the rulebook, the card wins. For example, the rules say creatures enter the battlefield untapped. But Imposing Sovereign is a creature that says 'Creatures your opponents control enter the battlefield tapped.' Imposing Sovereign changes the rules as long as it's on the ", "headingPath": "A  B · B Y O D", "sharpsignalDocId": 163}, {"page": 20, "score": 0.029437, "snippet": "You can play a Magic game with more than two players in it. There are dozens of different ways to do so. Some of the most popular are Two-Headed Giant and Commander, which can be played using only traditional Magic cards from your collection. Other multiplayer variants use oversized cards or a speci", "headingPath": "M V · T-H G · C · T · P · A", "sharpsignalDocId": 163}, {"page": 2, "score": 0.029418, "snippet": "In the Magic ™ game, you are counted among the elite spellcasters of the Multiverse-the Planeswalkers. Some are friends and others are foes. All wield terrifying magic and command armies of creatures torn from the endless planes of reality. Your deck of cards represents all the weapons in your arsen", "headingPath": "Ignite Your Spark", "sharpsignalDocId": 163}, {"page": 28, "score": 0.028283, "snippet": "The place where your mana is stored until you spend it or until the current step or phase ends. A series of games against the same opponent. Most matches are best two out of three, so the first player to win two games wins the match. The loser of the first game decides who goes first in the second g", "headingPath": "M  · M · M · M · M · M  · …", "sharpsignalDocId": 163}, {"page": 33, "score": 0.027885, "snippet": "One of the three types of abilities a permanent can have. See 'Triggered Abilities' on page 12. Each turn is divided into phases, and most phases have steps. See 'Parts of the T urn' on page 17. Beginning phase Untap step Upkeep step Draw step Main phase Combat phase Beginning of combat step Declare", "headingPath": "T  · T · Parts of the Turn · T-H G · T  · U · …", "sharpsignalDocId": 163}, {"page": 8, "score": 0.027237, "snippet": "If a spell or ability exiles a card, that card is put in a game area that's set apart from the rest of the game. The card will remain there forever, unless whatever put it there is able to bring it back. Exiled cards are normally face up. This zone is shared by both players.", "headingPath": "E", "sharpsignalDocId": 163}, {"page": 32, "score": 0.026294, "snippet": "A card type. See 'Sorcery' on page 5. Where damage or an ability came from. Once an ability has gone on the stack, removing its source doesn't stop the ability from resolving. All types of cards except lands are spells while you're casting them. For example, Serra Angel is a creature card. While you", "headingPath": "S · S · S · S · S · S  · …", "sharpsignalDocId": 163}, {"page": 27, "score": 0.02451, "snippet": "A keyword ability seen on creatures, artifacts, and enchantments. A spell with flash can be cast any time you could cast an instant. Italic text ( italic text looks like this ) in a card's text box that's just for fun. Flavor text sets a tone or describes part of the magical world of the card. If th", "headingPath": "F · F  · F · F · G · H · …", "sharpsignalDocId": 163}]
citations (raw): [{"page": 16, "quote": null, "headingPath": "Section 3: Playing a Game", "sharpsignalDocId": 163}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
answered-before recall: this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
debug row retained until: Oct 31, 2026 14:33

retrieval — what the search arm returned

score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.

per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.

token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.

fused rank	document	heading	page	fused RRF score	snippet chars
#1	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	A  B · B Y O D	p.15	0.030214 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#2	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	M V · T-H G · C · T · P · A	p.20	0.029437 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#3	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	Ignite Your Spark	p.2	0.029418 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#4	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	M  · M · M · M · M · M  · …	p.28	0.028283 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#5	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	T  · T · Parts of the Turn · T-H G · T  · U · …	p.33	0.027885 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#6	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	E	p.8	0.027237 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	275
#7	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	S · S · S · S · S · S  · …	p.32	0.026294 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#8	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	F · F  · F · F · G · H · …	p.27	0.02451 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Magic: The Gathering — Rulebook (corpus doc 163)	Section 3: Playing a Game	p.16	no quote on the wire

generation — timing and the path taken

timing split: retrieval 241 ms · first delta 8912 ms · total 10404 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 0 ms · retrieval 241 ms · ask 10152 ms · gateway work 10404 ms · total 10404 ms
tokens in (the prompt the answerer read): 4214
tokens out (what the answerer generated): 197
tok/sec: 135.4 tok/sec — 197 output tokens in 1.455 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 25s ago)
stream path: streamed — the gateway pushed at least one accumulated draft
watchdog: first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
num_ctx · think posture: both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.

disposition

outcome: ANSWERED — Answered
abstain rationale (n/a — this ruling answered): answered — no abstain rationale applies

setup-shape — why the checklist band did or didn't render

decision: NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
pattern that matched: SETUP — "setup" / "set up"
matched words (in the normalized question): set up

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 85), so "no registered errata card matched" above could never have matched one

Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.