{"serverId":"mcp-registry/ai.scoreia/open-labyrinth","tools":[{"name":"list_open_labyrinths","fixed":{"name":"list_open_labyrinths","description":"Local board. Adventure stories vs benchmark Wilson rates. Empty cell = not measured. Never a ranking.","inputSchema":{"type":"object","properties":{},"additionalProperties":false},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":63,"tokensAfter":63}],"toolsChanged":1,"tokensSaved":0,"todo":[{"tool":"enter_open_labyrinth","params":["host","mode","seed","origin","product","learn_from","model_claim","provider_claim"]},{"tool":"labyrinth_action","params":["direction","challenge_handle","expected_action_index"]},{"tool":"observe_labyrinth","params":["challenge_handle"]},{"tool":"seal_attempt","params":["challenge_handle","expected_action_index"]}],"note":"Deterministic fixes. Changes marked verify need a human look before shipping (renames, inferred annotations, inferred types, removed text). Parameter descriptions in `todo` need to be written by someone who knows the API."}