{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-18T13:45:35.999Z",
  "record_id": "VXI-EXT-PROCUREMENT-MCP-RESULT-ERROR-01-v1",
  "record_kind": "external_reference",
  "title": "MCP: A result envelope can contain a failed tool action",
  "system": "Model Context Protocol",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Does a successful MCP JSON-RPC result mean the underlying tool action succeeded?",
  "near_questions": [
    "Can an MCP result contain a business-logic failure?",
    "Where does MCP report a tool execution error?",
    "Does HTTP success prove an MCP action completed?",
    "Should isError true be counted as a completed tool action?",
    "What evidence closes the action after an MCP response?",
    "How do protocol errors differ from MCP tool failures?",
    "Can a returned result still contain an API error?",
    "What should an audit chain retain from tools/call?",
    "Does the JSON-RPC result field guarantee downstream success?",
    "How should an agent reconcile an MCP error response?",
    "Which tool outcome fields support a completion claim?",
    "Does a successful tool report independently prove its external effect?"
  ],
  "supported_claims": [
    {
      "claim": "MCP 2026-07-28 separates protocol errors from tool execution errors. API, validation and business-logic failures can be returned in a normal result with isError set to true. A JSON-RPC result envelope alone does not establish action success, and a reported success still needs the action-specific outcome evidence required by the buyer.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "Verified buyer configuration, actual data erasure, effective access or completed business actions",
    "Legal advice, compliance determination, vendor certification or safety assurance",
    "Runtime enforcement, permission to act or expanded licensed-checker coverage"
  ],
  "public_summary": "MCP 2026-07-28 separates protocol errors from tool execution errors. API, validation and business-logic failures can be returned in a normal result with isError set to true. A JSON-RPC result envelope alone does not establish action success, and a reported success still needs the action-specific outcome evidence required by the buyer.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "MCP: Tools",
    "source_url": "https://modelcontextprotocol.io/specification/2026-07-28/server/tools",
    "checked_on": "2026-10-18",
    "candidate_record_id": "VXI-EXT-PROCUREMENT-MCP-RESULT-ERROR-01-v1",
    "candidate_record_sha256": "1cde260446576709ff2dfe67835694ac69ed3c345c1becb05dac523bbf112f6b",
    "method": "Primary documentation reviewed for the published bounded statement.",
    "deployment_tested_by_varexis": false,
    "revalidation": "The delivered snapshot preserves the review date shown. Recheck current primary documentation and deployment context before relying on present applicability; payment does not trigger fresh research."
  },
  "answer_policy": {
    "classification": "DOCUMENTED_WITH_DEPLOYMENT_BOUNDARY",
    "bounded_answer": "MCP 2026-07-28 separates protocol errors from tool execution errors. API, validation and business-logic failures can be returned in a normal result with isError set to true. A JSON-RPC result envelope alone does not establish action success, and a reported success still needs the action-specific outcome evidence required by the buyer.",
    "required_buyer_context": "The correlated tools/call request and complete returned result. The isError value, result content and action-specific outcome fields. The downstream record or other evidence required to close the action. Buyer deployment not inspected.",
    "missing_evidence": "A broader claim needs evidence matching the intended use. Payment does not upgrade the evidence state."
  },
  "private_boundary": "Raw logs, thresholds, private paths, source code, protected mechanisms and reconstruction-level details are excluded from public and paid delivery.",
  "decision_profile": {
    "schema": "varexis-vendor-evidence-review/1",
    "review_status": "documentation_review_only",
    "checked_on": "2026-10-18",
    "claim_to_check": "Does a successful MCP JSON-RPC result mean the underlying tool action succeeded?",
    "documented_statement": {
      "status": "documented",
      "statement": "MCP 2026-07-28 separates protocol errors from tool execution errors. API, validation and business-logic failures can be returned in a normal result with isError set to true. A JSON-RPC result envelope alone does not establish action success, and a reported success still needs the action-specific outcome evidence required by the buyer.",
      "source_ids": [
        "mcp-tools"
      ]
    },
    "buyer_evidence_required": [
      "The correlated tools/call request and complete returned result.",
      "The isError value, result content and action-specific outcome fields.",
      "The downstream record or other evidence required to close the action."
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "Refuse a completed-action claim based only on transport or JSON-RPC success, or while a tool error remains unresolved."
    },
    "unknowns": "The buyer configuration, contract, effective entitlement and operational evidence have not been inspected. Missing evidence does not establish absence or failure of the feature.",
    "evidence_sources": [
      {
        "source_id": "mcp-tools",
        "url": "https://modelcontextprotocol.io/specification/2026-07-28/server/tools",
        "final_url": "https://modelcontextprotocol.io/specification/2026-07-28/server/tools",
        "title": "MCP: Tools",
        "checked_on": "2026-10-18",
        "captured_at_utc": "2026-10-18T13:33:51.059Z",
        "version_context": "MCP specification 2026-07-28",
        "sha256": "63ee3f828d75e719366501e90df16983440429a65751b20bd9c7e7f3649d7877",
        "bytes": 889820,
        "hash_basis": "Decoded HTTP response body bytes; identifies captured content, not truth or certification",
        "reviewed_sections": [
          "Does a successful MCP JSON-RPC result mean the underlying tool action succeeded?"
        ]
      }
    ],
    "observed_deployment": false,
    "commercial_reliance_boundary": "Procurement evidence support only; no supplier clearance, legal conclusion, configuration audit or verification of the buyer's claim is supplied.",
    "paid_value": {
      "decision_context": "An audit owner must classify tool execution outcomes from the tool result, rather than counting all received protocol responses as completed actions.",
      "free": "Complete review, practical questions, sources and limitations; may be saved locally.",
      "single_request": "Existing server-saved version-bound route snapshot for later authenticated retrieval.",
      "evidence_receipt": "The same snapshot plus the existing unsigned delivery receipt.",
      "excluded": [
        "Fresh vendor research",
        "Continuous monitoring or change alerts",
        "Testing the buyer configuration",
        "Private evidence or vendor certification"
      ],
      "integrity": "Hashes identify content versions; they do not prove truth or provide a signature."
    },
    "revalidation": {
      "trigger": "A saved purchase does not recheck the source or buyer configuration.",
      "specific_watch": "The correlated tools/call request and complete returned result. The isError value, result content and action-specific outcome fields. The downstream record or other evidence required to close the action."
    },
    "buyer_relevance": "An audit owner must classify tool execution outcomes from the tool result, rather than counting all received protocol responses as completed actions.",
    "refusal_conditions": [
      "Refuse a completed-action claim based only on transport or JSON-RPC success, or while a tool error remains unresolved."
    ]
  },
  "niche": {
    "label": "Agent Authority & Action Evidence",
    "niche_id": "agent-authority-action-evidence",
    "topic_id": "action-evidence-reconciliation",
    "buyer_intent": "An audit owner must classify tool execution outcomes from the tool result, rather than counting all received protocol responses as completed actions."
  },
  "paid_access_note": "The full published answer and boundaries are free. Paid access saves the selected route and source versions, with an unsigned receipt when purchased. Preview coverage before paying. Fresh research, bespoke assessment and protected evidence are excluded.",
  "service_route": {
    "request_guide": "/varexis-index/request.html",
    "request_workflow": "/varexis-index/request-workflow.json",
    "service_id": "single_request",
    "service_routes_url": "/varexis-index/service-routes.json",
    "payment_required": true,
    "availability_endpoint": "/api/index/capabilities",
    "operational_status": "AUTOMATIC_SERVICE_CAPABILITIES_GATED",
    "checkout_url": "/index-access"
  },
  "authority_boundary": "VAREXIS-INDEX informs evidence reliance. It does not provide advice, certification, deployment authority, security assurance, production approval, or guarantee.",
  "human_page": "/varexis-index/catalog.html#mcp-tool-result-error-not-protocol-success",
  "machine_readable_record": "/varexis-index/records/mcp-tool-result-error-not-protocol-success.json"
}
