Evidence row 276289

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Run a deterministic, lender-grade quick check on a real estate deal. Use this whenever a user asks whether a specific property or deal works, pencils, is worth pursuing, what their maximum offer should be, or wants real numbers on a flip, a rental refinance, or a ground-up build. Inputs: deal_type (FF | BRRRR | NC), purchase_price, arv_or_value (ARV for FF, refinance value for BRRRR, sellout for NC), rehab_budget, zip_code; optional annual_debt_service, noi_annual, units, units_to_hold. Returns a PASS, MARGINAL or FAIL verdict, the key financial metrics for that deal type (MAO and margin for FF, TPC and DSCR for BRRRR, TPC plus margin or DSCR for NC), and a one-paragraph summary. Every figure is computed exactly from formulas, identical to the underwriting pipeline behind Refpro's full deal pack: no estimates, no rounding shortcuts. Do not use for general questions about method, pricing or output formats; call methodology_faq instead. Results are a preliminary underwriting screen, not an appraisal and not a lender commitment.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "annual_debt_service": {
            "maximum": 10000000000,
            "minimum": 0,
            "type": "number"
          },
          "arv_or_value": {
            "maximum": 10000000000,
            "minimum": 0,
            "type": "number"
          },
          "deal_type": {
            "enum": [
              "FF",
              "BRRRR",
              "NC"
            ],
            "type": "string"
          },
          "noi_annual": {
            "maximum": 10000000000,
            "minimum": 0,
            "type": "number"
          },
          "purchase_price": {
            "maximum": 10000000000,
            "minimum": 0,
            "type": "number"
          },
          "rehab_budget": {
            "maximum": 10000000000,
            "minimum": 0,
            "type": "number"
          },
          "units": {
            "maximum": 9007199254740991,
            "minimum": 0,
            "type": "integer"
          },
          "units_to_hold": {
            "maximum": 9007199254740991,
            "minimum": 0,
            "type": "integer"
          },
          "zip_code": {
            "pattern": "^\\d{5}$",
            "type": "string"
          }
        },
        "required": [
          "deal_type",
          "purchase_price",
          "arv_or_value",
          "rehab_budget",
          "zip_code"
        ],
        "type": "object"
      },
      "name": "deal_quick_check"
    },
    {
      "description": "Fetch a sanitized example of Refpro's 1-Page Deal Sheet, the single lender-facing page a borrower hands to a lender. Use this when a user asks what a Refpro deal sheet looks like, what to hand or send a lender, or wants a one-page summary format for a flip, a rental refinance or a ground-up build. Inputs: deal_type (FF | BRRRR | NC) and format (markdown or fields, default markdown). Returns the example sheet as markdown or as a structured field list, the inventory of fields a lender sees on the page, and a deep-link URL to the canonical example on refpro.ai. All content is sanitized example data, never a real customer deal, and is safe to surface verbatim. Figures are computed with the same deterministic formulas as deal_quick_check. No network calls; examples load once at module init. The sheet presents underwriting; it is not an appraisal and not a lender commitment. Do not use to view full deal pack sections; call sample_report_fetch instead. Do not use to analyze the user's own deal; call deal_quick_check instead.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "deal_type": {
            "enum": [
              "FF",
              "BRRRR",
              "NC"
            ],
            "type": "string"
          },
          "format": {
            "default": "markdown",
            "enum": [
              "markdown",
              "fields"
            ],
            "type": "string"
          }
        },
        "required": [
          "deal_type"
        ],
        "type": "object"
      },
      "name": "deal_sheet_preview"
    },
    {
      "description": "Answer questions about how Refpro works. Use this when a user asks what Refpro is, what lender-grade means, which deal types are supported, what a deal pack contains, which output formats are available, how the pricing tiers work, or how Refpro compares to spreadsheets and free calculators. Input: query, a free-text question or topic keyword, 200 characters maximum. Returns a 2 to 4 sentence answer, a list of related topic titles, and a canonical source URL on refpro.ai. Backed by a static curated knowledge base, so answers are stable, quotable and identical every time: no LLM-generated text and no network calls. Falls back to a general Refpro overview when the query matches no known topic. Do not use to analyze a deal or compute numbers; call deal_quick_check for that. Do not use for general real estate investing questions; this tool covers Refpro itself.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "query": {
            "maxLength": 200,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "methodology_faq"
    },
    {
      "description": "Fetch a sanitized public sample section from Refpro's reference deal library. Use this when a user asks to see what a Refpro report or deal pack actually looks like, wants an example before signing up, or needs a reference for how a lender-ready underwriting package is structured. Inputs: deal_type (FF | BRRRR | NC) and section (summary, financials, risk_notes or full). Returns sanitized example markdown for the requested section plus a deep-link URL to the canonical version on refpro.ai. The full section stitches summary, financials and risk_notes in order. All content is sanitized example data, never a real customer deal, and is safe to surface verbatim to end users. No network calls; samples load once at module init. Do not use to analyze a user's own deal; call deal_quick_check for that.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "deal_type": {
            "enum": [
              "FF",
              "BRRRR",
              "NC"
            ],
            "type": "string"
          },
          "section": {
            "enum": [
              "summary",
              "financials",
              "risk_notes",
              "full"
            ],
            "type": "string"
          }
        },
        "required": [
          "deal_type",
          "section"
        ],
        "type": "object"
      },
      "name": "sample_report_fetch"
    }
  ]
}

What the leaf hashes

{"body":"684133035d833b7f726b35e15fc1bb4e3bdbb343b551603c67ec50d893f73fa4","id":276289,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793041182629120,"prev":null,"subject":"e0e8d3ca-f564-4179-90b4-43a7f43cbc5c","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-26 (296695 rows).

1. 0x848a6cab358312f940c0e26a7b7f9aaf43e892e1e9f8f28971ba4c940239175a
2. 0x6f595ef13e2262619ba7a60646db3e95f4782a20b793c23ec1e70f592c4ca1bb
3. 0xe0109628e7f89e81456ffa0408a10e6ede483dde8d0f0373c6aa1f1c7090a0fe
4. 0xdd136a1432692dadb26f3557eebb4bfd855c9748207a70e364eae1edc672a4d4
5. 0x7663e1a617ce27519d1cdf9c4d72b7cd47b26d4ce59a6e0590f623a330857d61
6. 0xb6a5b336b10d43397c52edee1521b8bdfb0f227c7258b677176fd5342aa789c5
7. 0xabcebae630b061dfd5defc3ca4c7a71d653500ae627c27d81764ec65d7735b79
8. 0x1ee6c1386f40a5635cfc7ef2bd47cf215f72ffd97a6a9d59c787e72300e0b0a2
9. 0x6f20f3f96eb5fe347acc5dc3faf1cd2aaeb54dd43030bce2efc76fa38c29ea26
10. 0xbd61f8ccc42a3dedbb87058ee9b8aa973f0189e5171c2843edd9ca490c36ad87
11. 0xdb4295ae338449b07243daebee8c36f16b3aaca1599a8f860eb80e22bca21e79
12. 0xfdaa032291ded0df2cf35d6e9dc6e7a2643d0fe027dd3ab321971f1f7bf69147
13. 0x91c2ae93ec20c7fed5088112fe3941ca622dfb3f8f1022c4844726c361244bd4
14. 0x0eff463856b0992d53ab7d8c0b97c71541413358bdd445710c1e4b6aeb4d8f78
15. 0x7eb603d37f0f22dae1ea013e391889906ffc0139ff26e25b044bee38eec8f9b2
16. 0x2b6e23e3624a1b66e1d2298cfbce99a93ce6b13d24a58112a71802d79c5f7a76
17. 0xd21942ae3214eff88e08ab04884fd4b11958b51af9a0741b7668e2d07a2c56c9
18. 0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae