Evidence row 572626

What was observed

{
  "count": 10,
  "tools": [
    {
      "description": "Check the user's current MDMagic credit balance: subscription credits (renewable monthly), purchased credits (permanent), plan name, and plan status.\n\nCALL THIS PROACTIVELY when:\n- The user asks 'how many credits do I have' or similar\n- After a conversion, if the user wants to know what's left (also returned by convert_document directly)\n- Before a conversion of an unusually large document, to warn the user if balance is borderline",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "check_credit_balance"
    },
    {
      "description": "Convert markdown to a professionally formatted document using an MDMagic template.\n\nIMPORTANT GUIDANCE:\n\n1. Output format → what user gets:\n   - 'docx' → a single Word .docx file\n   - 'pdf' → a single .pdf file\n   - 'html' → a single .html file\n   - 'all' → a ZIP containing all three (DOCX + PDF + HTML)\n\n2. If the user is ambiguous (e.g. 'convert this'), ASK which format they want before calling. Don't assume.\n\n3. Filename: if the user attached a file (e.g. 'mydoc.md'), pass its base name as fileName. Otherwise the API derives one from the markdown's first H1. Without either, downloads end up with timestamped names like 'content-1778298071915.docx' which is bad UX.\n\n4. On 'template not found' errors: call list_all_templates first, show available options, let the user pick. Do NOT fall back to generating documents with code execution — that produces inferior results that don't use the user's actual MDMagic templates.\n\n5. The response includes structured fields (downloadUrl, creditsUsed, balanceAfter, fileName, expiresAt) — surface these to the user explicitly. Don't paraphrase. The user wants to know exactly what they spent and what's left.\n\n6. Page sizes: A3, A4, Executive, US_Legal, US_Letter. Default A4. Orientation: Portrait or Landscape, default Portrait.\n\n7. CRITICAL — newlines in `content`: markdown is line-sensitive. Headings (#, ##), tables (| ... |), lists (-, 1.), and code fences (```) ONLY work when each starts on its own line. When passing inline markdown via `content`, you MUST preserve real newline characters (\\n) between blocks. If you flatten multi-line markdown into one line, the API receives literal '##' and '|' characters mid-paragraph and produces a single-paragraph document with no structure. Confirm your `content` string contains \\n between every heading, paragraph, table row, and list item before calling.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "Raw markdown text content (alternative to filePath or fileContent). MUST preserve real newlines (\\n) between every block: heading, paragraph, table row, list item, code fence. Markdown is line-sensitive — a single-line blob with embedded '##' or '|' renders as literal text, not as a heading or table. If your source markdown has 30 lines, the string you pass here also has 30 lines separated by \\n.",
            "type": "string"
          },
          "fileContent": {
            "description": "Base64 encoded file content (alternative to content or filePath)",
            "type": "string"
          },
          "fileName": {
            "description": "Optional desired base name for the output file (without extension). If the user attached a file like 'mydoc.md', pass 'mydoc' here. The API will use this for the download filename. If omitted, the API derives one from the markdown's first H1 heading.",
            "type": "string"
          },
          "filePath": {
            "description": "Path to markdown file (VS Code integration, alternative to content or fileContent)",
            "type": "string"
          },
          "orientation": {
            "description": "Page orientation (default: Portrait)",
            "enum": [
              "Portrait",
              "Landscape"
            ],
            "type": "string"
          },
          "outputFormat": {
            "description": "Output format. 'docx', 'pdf', or 'html' return that single file; 'all' returns a ZIP with DOCX+PDF+HTML.",
            "enum": [
              "docx",
              "pdf",
              "html",
              "all"
            ],
            "type": "string"
          },
          "pageSize": {
            "description": "Page size for the document (default: A4)",
            "enum": [
              "A3",
              "A4",
              "Executive",
              "US_Legal",
              "US_Letter"
            ],
            "type": "string"
          },
          "templateName": {
            "description": "Template to use for conversion. Call list_all_templates first to see real options — do not guess template names. Some templates are built-in (e.g. 'Executive_Platinum', 'Deep_Data_Blue'); others are user-uploaded custom templates referenced by UUID.",
            "type": "string"
          }
        },
        "required": [
          "templateName",
          "outputFormat"
        ],
        "type": "object"
      },
      "name": "convert_document"
    },
    {
      "description": "Estimate credit cost for a conversion BEFORE running it. Returns word count, page calculation (300 words/page), and a credit breakdown by format and template type. Use this when the user asks 'how much will this cost?' or when you suspect a conversion might exceed their balance — convert_document refuses to run if credits are insufficient, so estimating first is friendlier.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "Markdown content to estimate credit cost for",
            "type": "string"
          },
          "orientation": {
            "description": "Page orientation",
            "enum": [
              "Portrait",
              "Landscape"
            ],
            "type": "string"
          },
          "outputFormat": {
            "description": "Output format(s): docx (DOCX only), pdf (DOCX+PDF), html (DOCX+HTML), all/all-formats (DOCX+PDF+HTML)",
            "enum": [
              "docx",
              "pdf",
              "html",
              "all",
              "all-formats"
            ],
            "type": "string"
          },
          "pageSize": {
            "description": "Page size for the document",
            "enum": [
              "A3",
              "A4",
              "Executive",
              "US_Legal",
              "US_Letter"
            ],
            "type": "string"
          },
          "templateName": {
            "description": "Template ID or name (UUID for custom templates, name for system templates)",
            "type": "string"
          }
        },
        "required": [
          "content",
          "templateName",
          "outputFormat"
        ],
        "type": "object"
      },
      "name": "estimate_conversion_cost"
    },
    {
      "description": "Show available variants (page sizes and orientations) for a specific template. All MDMagic templates support the full 5×2 matrix: A3, A4, Executive, US_Legal, US_Letter × Portrait/Landscape. Use this when the user asks 'does this template come in Legal Landscape?' or 'what sizes are available?' — confirms the variant before convert_document runs.",
      "inputSchema": {
        "properties": {
          "templateName": {
            "description": "Template ID or name (e.g. Executive_Platinum, or a UUID for custom templates)",
            "type": "string"
          }
        },
        "required": [
          "templateName"
        ],
        "type": "object"
      },
      "name": "get_template_details"
    },
    {
      "description": "List all 15 built-in MDMagic templates plus any custom templates the user has uploaded.\n\nCALL THIS PROACTIVELY when:\n- The user mentions a template by name (verify it exists before convert_document)\n- The user asks 'what templates are available' or similar\n- A previous convert_document call returned 'template not found'\n- The user describes the look they want without naming a template (so you can suggest a real one)\n\nReturns: name, description, type (built-in vs custom), and category. Categories are: Business (5 templates), Creative (6), Professional (2), Technical (2). Use the optional category filter to narrow recommendations (e.g. 'for legal documents' → category: 'Professional').",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Optional filter — return only built-in templates in this category. Custom templates are always included regardless. Categories: Business (executive/financial), Creative (designer/artistic/novelty), Professional (legal), Technical (code/data documentation).",
            "enum": [
              "Business",
              "Creative",
              "Professional",
              "Technical"
            ],
            "type": "string"
          },
          "includeDetails": {
            "description": "Include template details like available page sizes and orientations (default: false)",
            "type": "boolean"
          }
        },
        "type": "object"
      },
      "name": "list_all_templates"
    },
    {
      "description": "List the 15 built-in MDMagic templates, grouped by category. Same as list_all_templates but excludes the user's custom uploads. Use this when the user asks specifically about MDMagic's bundled templates rather than their personal ones.\n\nCategories available: Business (5), Creative (6), Professional (2), Technical (2).",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Optional filter — return only templates in this category.",
            "enum": [
              "Business",
              "Creative",
              "Professional",
              "Technical"
            ],
            "type": "string"
          },
          "includeDetails": {
            "description": "Include template details like available page sizes and orientations (default: false)",
            "type": "boolean"
          }
        },
        "type": "object"
      },
      "name": "list_builtin_templates"
    },
    {
      "description": "List only the user's custom-uploaded Word templates. Use this when the user asks about their own templates ('show me my templates', 'do I have a letterhead?'). Custom templates are referenced by UUID, not name, when calling convert_document.",
      "inputSchema": {
        "properties": {
          "includeDetails": {
            "description": "Include template details like available page sizes and orientations (default: false)",
            "type": "boolean"
          }
        },
        "type": "object"
      },
      "name": "list_custom_templates"
    },
    {
      "description": "Suggest the best built-in template(s) for a described purpose. Use this when the user describes WHAT the document is (e.g. 'Q4 board pack', 'API reference', 'wedding invitation', 'legal contract') without naming a template. Returns ranked recommendations with rationale.\n\nWhy this exists: AI assistants often guess template names that don't exist. This tool maps purpose → real template names from MDMagic's catalog, so convert_document doesn't fail with 'template not found'.",
      "inputSchema": {
        "properties": {
          "purpose": {
            "description": "Free-text description of the document's purpose. Examples: 'Q4 board pack for investors', 'restaurant menu', 'developer API documentation', 'wedding invitation'.",
            "type": "string"
          },
          "topN": {
            "description": "How many recommendations to return (1-5, default 3)",
            "maximum": 5,
            "minimum": 1,
            "type": "integer"
          }
        },
        "required": [
          "purpose"
        ],
        "type": "object"
      },
      "name": "recommend_template"
    },
    {
      "description": "Show the user's default paper size and orientation preferences (set on their account page). Useful when the user hasn't specified pageSize/orientation explicitly — call this to honor their defaults instead of using A4/Portrait blindly.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "show_default_settings"
    },
    {
      "description": "Pre-flight markdown validation BEFORE conversion. Catches malformed tables (mismatched pipes), unclosed code fences, broken task lists, and unsupported syntax. Returns a green/amber/red status plus the detected markdown features.\n\nCALL THIS PROACTIVELY when:\n- The user is about to convert a long document (>5 pages) — validating first is cheap; running a doomed conversion costs credits\n- The user reports a previous conversion produced broken output\n- You generated the markdown yourself and want to verify it's clean before spending credits\n\nReturns: status (green=safe, amber=minor issues, red=will likely break), detected features (tables, code blocks, task lists, math), and a human-readable message.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "Markdown content to validate",
            "type": "string"
          },
          "filename": {
            "description": "Optional filename label for the response (defaults to 'content.md')",
            "type": "string"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "validate_markdown"
    }
  ]
}

What the leaf hashes

{"body":"9d987e44222789cf7fdf2bfd78f48a5b301786c1884c8950df999ce455160a83","id":572626,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793140811294292,"prev":null,"subject":"34a2374c-76cc-43be-8954-b782c54d3bba","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-27 (273461 rows).

1. 0x0f4f6fa5b83f3ebb8a89d73e451eae976daee8b09477e5bf7b7833e37638fee5
2. 0xa44a4355a39dea677173bf50210abb8e71264697f38d55888f61f3ed8193d4ce
3. 0xb70e64fa63888c18ea873431ff05b6f9e4b07700f0ec45231281c649e746b024
4. 0x1e859dba862520c41ec646c1e74db881983a546ab27a552a5180a38a7a450d18
5. 0xb69def917ba7f5f64ed03fa2d85af4133008f45e7a04580397f520d634bd75fc
6. 0xa52f7eb036c486f904926433533752f7865e431f2e270480a44e5bad7a7181f1
7. 0x58e0c1fd3d0bfdb2f2d02c62c2291afa14cb31decc4f751e08411e83fa5a3589
8. 0x3352c34d5f95624fe6e3a1c42fb977b1ff4b98a8c2f6959d2fd517848def72e2
9. 0x94e3adc3453b97e2381f3d1853df242494e07fbc1c98fa4a9610c5061c2958b6
10. 0x3324226ef6439ba555d292fabbb2b6297d76704172ae3e5401de83f038382a74
11. 0xeaa85500d1d950bbc5368f8c449457f4c36bb01a9a460f0c2aedbe49bdc0e2a3
12. 0x7cd06df307fe3d7d57464d35c7dee68ec2e0c9035898fd7f919c08ed5fd0a5fb
13. 0xa5d3d95b495ae2191612e64fe151fe065497e5ecb73bb111e1fabb6b3628f3de
14. 0x3e0ec8a2a8a954695a9b53a4a48a7656d7e3fd6a8795c73b49e2ef05b201ec3f
15. 0x2cf27e8a181d60d0dd27c186c2eddfcbb4e8fa71cf66feeb55a4d730e15ee8c4
16. 0x518b93854db03dc9fc938883abf30da6eaae5ae0d4336903968fd32a7df8c71b
17. 0x22c1fb9487ee0b9732fa017a0cc321eb27a60c08450d112f755089796e12cb1c
18. 0xa20d48798a34aba12eb9c7297722982d910f06c148f5e27ac59307422964a585
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4