{"id":299245,"recorded_at":"2026-10-26T22:11:15.870910Z","observed_at":"2026-10-26T22:11:15.870846Z","subject_kind":"endpoint","subject":"b65a65bc-cf9f-4c9e-a9ba-628810512d8f","kind":"mcp.tools","method":"probe.mcp/1","body":{"count":1,"tools":[{"description":"Estimate a causal effect from a dataset and answer a business question.\n\nProvide exactly one of ``csv`` (CSV text) or ``data`` (list of row objects).\nReturns the full long-form Pulse report (the same answer an email reply\ncontains) as the primary text content and as ``report`` in the structured\nresult, followed by chart PNGs as image content blocks (unless\n``include_charts`` is false). Structured fields: the adjusted effect size\n(``ate``/``effect_size``) with its confidence\ninterval (``ci_low``, ``ci_high``, ``ci_range``), per-channel effects\n(``channels``, keyed by outcome), confidence, and caveats. A ``test_design``\n(how long a spend-cut test would take to confirm the effect, and whether the data\nalready suffices) is included only when the question asks about sample size,\npower, or how long a test would take, or when ``include_test_design`` is true;\notherwise it is null. With ``include_guardian_verdict`` it also returns\n``guardian_verdict`` ``{verdict: pass|caution|hold, reason}``, computed locally.\nAll numbers are deterministic statistics, never LLM-generated.\n\nArgs:\n    question: The business question, e.g. \"Does ad spend drive sales?\".\n    csv: Dataset as CSV text.\n    data: Dataset as a list of row records (alternative to ``csv``).\n    cause: Treatment column (inferred from the question if omitted).\n    effect: Outcome column (inferred if omitted).\n    confounders: Columns to adjust for, in addition to those discovered.\n    outcomes: Several outcome columns, for by-channel effects.\n    time_col: Time column (used for the test-design cadence).\n    include_guardian_verdict: Also return a pass/caution/hold verdict.\n    include_charts: Attach chart images (DAG, effect, trend) as image content.\n    include_test_design: Force the spend-cut test design / sample-size section on\n        (true) or off (false). Omit (null) to include it only when the question\n        asks about sample size, statistical power, or how long a test would take.\n","inputSchema":{"properties":{"cause":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Cause"},"confounders":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"default":null,"title":"Confounders"},"csv":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Csv"},"data":{"anyOf":[{"items":{"additionalProperties":true,"type":"object"},"type":"array"},{"type":"null"}],"default":null,"title":"Data"},"effect":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Effect"},"include_charts":{"default":true,"title":"Include Charts","type":"boolean"},"include_guardian_verdict":{"default":false,"title":"Include Guardian Verdict","type":"boolean"},"include_test_design":{"anyOf":[{"type":"boolean"},{"type":"null"}],"default":null,"title":"Include Test Design"},"outcomes":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"default":null,"title":"Outcomes"},"question":{"title":"Question","type":"string"},"time_col":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Time Col"}},"required":["question"],"title":"pulse_analyzeArguments","type":"object"},"name":"pulse_analyze"}]},"body_sha256":"0c9e5b94badec74e69189d8b2574ed7e17470a29f38571b3e0b5394f70709940","prev_id":null,"leaf":"0xd7d2f69a6f013e4307ec0926d852163a44b6bed1a3aa6c441769b74a178ade72","leaf_text":"{\"body\":\"0c9e5b94badec74e69189d8b2574ed7e17470a29f38571b3e0b5394f70709940\",\"id\":299245,\"kind\":\"mcp.tools\",\"method\":\"probe.mcp/1\",\"observed_us\":1793052675870846,\"prev\":null,\"subject\":\"b65a65bc-cf9f-4c9e-a9ba-628810512d8f\",\"subject_kind\":\"endpoint\"}","day":{"day":"2026-10-26","leaves":296695,"root":"0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8","chained":"0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a","anchor_chain":"eip155:5042002","anchor_tx":"0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae","anchor_block":69251483},"proof":["0xd7d30ccb66c61513b5b24dfaa1b2847dc6549cfb5d051dfff56846d7d9f9348a","0x49fbc87fc4546ec023e9c216617a52bb815a65bbffb354621fb76a1d30af66ab","0x393d7293a2bc5f8add479f428b3d37d582d3e8d532dad144adbb30c0b2ddfb71","0xf50cf268c073cdbe9d4c17a2db68f53730011c7921192fbefbc1c801b0852fa9","0x46e0f74fd261d16b12e1812234d43aba1572cc3da5bb457b8a249f6ab70eb8a6","0xa4901d6d751b0678b5c1d1f962c4f202776bf745ac85c4360b7c9d9c9c28262c","0x20e7d9243d1b30a5b3e22533c7d1c118c07082fbe4e7e1f93d5582aac3557a37","0x491ffb22b6faa4f27b3abcc2471784d7fa0064d960525b5463a4ef5fb68217a3","0x421ef9a649a8881c0ca743e8fda5d3c2a2f63232806f1fbb0768307d8cca1f0b","0x99d243e75489137f42f22b35cac536858bfa54cac8df9dedbb78852b9f686a91","0x2671a86f48dece064e871ca46396549de6c07bd09915bed27b7ac95a735127fd","0x07e91966e8a0c43a0725bd3d523259064a93333c2900e6171b69ffbfd9f423f1","0xcd9e3af1fa905ec61b99ee9442716d7c7a439aecacd018ec229a24def1cabf6b","0x6b927d53caa5125cdba9255612d524976c691f8672796c3f0885ba2c5b3af1ad","0x6dc40f983a3840a0ad927a9ca17f4ff1e3b649a6c735e2a09b140db7c2caf13b","0x703f95866af09c5e5d6ead7411e9a10f964a41a2aff64d4a55ff0053c023a023","0xd0651cb9bc8155eb52b5247d506e74b8a935057dc190ba52091702ac25ed3a40","0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f","0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a"]}