Evidence row 574388

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Cancels the task, as long as the specialist has not started work yet.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "task_id": {
            "type": "string"
          }
        },
        "required": [
          "task_id"
        ],
        "type": "object"
      },
      "name": "cancel_task"
    },
    {
      "description": "Invites one or more chosen specialists to a project — does NOT charge payment. budget is a single amount for the whole task (not multiplied per specialist) — whoever accepts it does the work for it. Requires user_confirmed=true, set only after the user has explicitly confirmed in the conversation the choice of specialists, the list of shared files and the estimated cost. Estimate budget yourself from the problem's complexity (e.g. 1h = a single well-localized bug / a simple document fix / a minor graphic tweak; 2h = a standard debug across a few files / a draft legal document (e.g. Privacy Policy) / a landing page design; 3h = an architecture review, a full legal package (ToS+Privacy+GDPR) or a compliance audit, full branding, no clear diagnosis) times the specialist's min_rate_per_hour (from search_specialists) — this field is informational, not enforced, always in USD (the only currency on the marketplace).",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "budget": {
            "minimum": 0,
            "type": "number"
          },
          "context_files": {
            "description": "The minimal set of files the specialist needs. Each entry is { name, url?, content_base64? } and must carry exactly one source. `url` is strongly preferred: pass a link if the user gave one (Google Drive / Dropbox / S3 / raw GitHub) — the server rewrites common Google Drive and Dropbox share links to their direct-download form, and rejects a URL that returns a web page instead of a file — or, if you have a way to upload the file yourself (e.g. a code execution / shell environment) — upload it to any URL-reachable location first and pass that link instead of the raw bytes; the server just downloads it, which is fast and costs you almost no extra tokens. Use `content_base64` only as a last resort, when there is no URL and you have no way to produce one yourself (e.g. a small file the user attached directly in a chat-only client with no upload capability of its own) — inlining bytes means writing out the entire file as text, which is slow and burns far more tokens than a URL for anything beyond a tiny file. Before falling back to it, tell the user that creating the task will take noticeably longer and use more tokens because of it. Raw base64 only, never a `data:...;base64,` prefix. This server runs remotely and cannot read the caller's disk, so never pass local paths. The server scans every file for secrets, then uploads the rest to the task's file storage on Stoory; contents never enter the model context. Max 5MB per file. Entries that are unreadable or filtered as secrets come back in blocked_files — the task is still created without them.",
            "items": {
              "additionalProperties": false,
              "properties": {
                "content_base64": {
                  "type": "string"
                },
                "name": {
                  "type": "string"
                },
                "url": {
                  "format": "uri",
                  "type": "string"
                }
              },
              "required": [
                "name"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "description": {
            "type": "string"
          },
          "language": {
            "description": "The task's language — must match the language the user phrased title/description in (there is no auto-detection, set it according to the user's input).",
            "enum": [
              "English",
              "Polish",
              "French",
              "German",
              "Spanish",
              "Italian"
            ],
            "type": "string"
          },
          "problem_context": {
            "type": "string"
          },
          "specialist_ids": {
            "description": "Id of one or more specialists to invite.",
            "items": {
              "type": "string"
            },
            "minItems": 1,
            "type": "array"
          },
          "timeline": {
            "default": "No rush",
            "description": "How urgent the project is from the client's perspective — ask the user directly, do not guess.",
            "enum": [
              "In a week",
              "In a month",
              "In 3 months",
              "No rush",
              "Do not know"
            ],
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "user_confirmed": {
            "description": "Must be true — set it only after the user's explicit confirmation in the conversation.",
            "type": "boolean"
          }
        },
        "required": [
          "specialist_ids",
          "title",
          "description",
          "problem_context",
          "budget",
          "language",
          "user_confirmed"
        ],
        "type": "object"
      },
      "name": "create_task"
    },
    {
      "description": "Returns the whole task record in one call — use it both to check progress and to read the result. Fields: status, title, desc, budget, deadline, timeline, created, modified; specialist_invited and specialist_accepted (arrays of { id, profile_url } — profile_url is already in the right language, show it to the user as a link, not a bare id); and `files` — URLs of every file attached to the task on Stoory (the client's context files plus whatever the specialist delivers). Call it again when the user asks about progress. create_task already returns attached_files for the files it uploaded.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "task_id": {
            "type": "string"
          }
        },
        "required": [
          "task_id"
        ],
        "type": "object"
      },
      "name": "get_task"
    },
    {
      "description": "Searches for specialists in the Stoory marketplace via semantic search. Result quality depends mostly on a well-built `query` — see the `query` field description. If a result has <3 hits or only 'Alternative fit', retry with a simpler/broader query (see `query`) instead of asking the user; only after about 3 failed attempts tell the user you have no one to recommend for these requirements and suggest widening the criteria.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "country": {
            "description": "Only when the user explicitly asks for the specialist's country (e.g. 'a designer from Poland'). Full English country name, e.g. \"Poland\", \"Germany\" — not an ISO code. Ignored if geo_location is also given. Omit the field when the user did not mention a country.",
            "type": "string"
          },
          "geo_location": {
            "additionalProperties": false,
            "description": "Only when the user gives a specific city/location and wants to search nearby (e.g. 'near Warsaw', 'a designer in Warsaw'). An object { lat, lon, radius_meters } — determine the lat/lon of the named city yourself. Default radius_meters is 50000 (50km); when there are too few results, raise it to 100000, then 200000 instead of broadening the query. Takes priority over `country` if both are given. Omit the field when the user did not mention a location.",
            "properties": {
              "lat": {
                "type": "number"
              },
              "lon": {
                "type": "number"
              },
              "radius_meters": {
                "type": "number"
              }
            },
            "required": [
              "lat",
              "lon",
              "radius_meters"
            ],
            "type": "object"
          },
          "languages": {
            "description": "Only when the user explicitly asks for a specific specialist language (e.g. 'a Polish-speaking designer'). Allowed values: English, Polish, German, French, Spanish, Italian — any other value is rejected by the API. Omit the field (or []) when the user did not mention a language.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "limit": {
            "description": "Default 10, raise to 20 for weak results or when the user asks for more options (max 20).",
            "maximum": 20,
            "minimum": 1,
            "type": "number"
          },
          "query": {
            "description": "The specialist's role and skills, MAX 12 words, natural language — not a full sentence describing the user's problem. In English if possible (faster response and better hits than other languages). Good: 'Senior Stripe developer', 'Professional logo designer', 'Experienced UX designer for mobile apps'. Bad: 'I need someone who can help me with branding and visual identity design' (full sentence instead of a role), 'Full-stack developer with microservices architecture experience' (too much glued-together specificity at once). When results are weak (<3 hits or only 'Alternative fit'), retry with a progressively simpler/broader query instead of asking the user, e.g. 'Senior mobile app developer for fintech startup' → 'Mobile app developer' → 'App developer' → 'Mobile development'; or 'GDPR compliance lawyer for healthcare startup' → 'GDPR lawyer' → 'Data protection lawyer' → 'Lawyer'.",
            "maxLength": 120,
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_specialists"
    }
  ]
}

What the leaf hashes

{"body":"a445a9c0dec20699f588b46befeb9263a818f319df0ebc70b956ae974f533e1c","id":574388,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793141511320847,"prev":null,"subject":"9edb33ef-379d-46e3-961f-706430f6c2da","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. 0x592547e1bb39eb11af5f92a0caf53e13952c4ede154047a6b5c176bea13ae9b7
2. 0xfcf0067ba0bbc1a1cefe9529eefa770d60e3bfb016a454bf17bc18d7f6686be7
3. 0x5f8670f6fbb1c90503f320e5ed015fbd701863c48ef195d62c0a7711d00a764c
4. 0x4cdca66e7c19063fe31d49677557e61e3d9e2bcf57f81eec240564a113ad6c8b
5. 0x405231669fa4047e0f0e5958b9bda22e19dabe4956a7059059d950ee840411e8
6. 0xbbf99fbb1028eb02e4ce1a2cbcd79af63cbdd572d65c1aa74100662511b3a7c1
7. 0xbe949c2747161f5166f02d55d8ee6a31fde8af2573f168a8e9c470ab8e6564b1
8. 0x28f6a62be7bfef73176c528f552610426f3fea50856344d2968853a0c0828025
9. 0x65485f3843c05fe643cdfd3e5a113cb894a6a5491a4c1f2abdc4479282ad079d
10. 0x7e1b9e14e6163c14ee78839d55690d07d8aa2e81481fdf9840c943f2e2833a05
11. 0x095b40edf800595a91733b7d7641dc11c53f74bc29c345d97d171068bd13ee53
12. 0x6f9c2e17fd073d07da42da76c8ca2f200b30027f0378b0d9628f8fac6f48cd16
13. 0x5b3213451efe1e2950dd287afaede00cc8a45dfd9721ef9b3d698bde1eeb9909
14. 0x674bc1173d39130be4d15bbfc7327f8a8af87eb251e54c8d4409c7e840b9e538
15. 0xb78ea6a255dd06e2f402a1a733bca392fa6243920bcba95e8b80bdfc6ce5f553
16. 0x3ed50f053eca72dfd3a9d45a11935240bfe691e57835c367ddebe2cbc49efe9d
17. 0x0e01aa9525097570a6edaf32bfc959de57bf5c24317cf10c0716affea85ca60d
18. 0xa20d48798a34aba12eb9c7297722982d910f06c148f5e27ac59307422964a585
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4