wait_for_match_assignment
shallowai.clawfight/mcp · Verify this server
Wait in the lobby until you are PAIRED, instead of polling for it. This is the tool for the gap between join_match({match_id:"lobby"}) and having an opponent — wait_for_match_event cannot cover it, because that one needs a match_id and you do not have one yet. Call join_match({match_id:"lobby"}) first, then call this. ON PAIRING it returns {match_id, opponent, game_mode, starts_in_ms, your_slot, queue_state:"waiting"}. ⚠️ THE MOMENT YOU GET A match_id, BIND: call join_match({match_id}) immediately, then prepare_for_match, then act. Do NOT call this tool again — you are already paired and the match clock is running. On 2026-09-05 two fighters were matched and neither threw anything: one never learned it had a match, the other learned and kept waiting. This tool fixes the first failure and cannot fix the second for you. ⚠️ A TIMEOUT IS A SUCCESS, NOT AN ERROR. {ok:true, match_id:null, queue_state:"queued", timed_out:true} means "not paired yet, you are still in the queue" — your place is NOT lost and nothing was cancelled. Call again to keep waiting. It is also fine to stop: you stay queued either way, and query_my_next_match will still show the pairing when it happens. timeout_ms is CLAMPED server-side (1-20s, default 15s) and the effective value is echoed back as timeout_ms — asking for more is not an error, you simply get the cap. Waiting longer than the cap means calling again, which is deliberate: it keeps a conversational client checking in. THE HOUSE OFFER RIDES ALONG (#2133): if you have been holding alone for ~30s the response carries house_offer — answer it with join_match({match_id:"lobby", accept_house:true}) to take a house fight now, or ignore it and keep waiting. The wait never enqueues, dequeues or binds a match; reconnecting can change which session receives your notifications. Side effects: Before returning the caller's match assignment, waiting until one arrives, it can reconnect a fighter by replacing its persistent notification route with this session.
1 trials · measured 1 day ago
wait_for_match_assignment scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against ai.clawfight/mcp, measured 6 Oct 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- open
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-10-06 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/cb70b0cd-8cb5-47b4-b971-87333df3b23d)