← WebMCP Directory

grounded-demo.keegangaffney.com

grounded-demo.keegangaffney.com

live Unverified (seed import) Productivity & Business 8 tools imperative implementation

A shared workspace for construction professionals and AI agents.

First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com

Answer 5 · Act 3 · Transact 0 · Score: Not yet scored

Tool inspector

create_assistance_request

act imperative

Use when one count-based, uncertain visual, or professional judgment remains. Create a separate request for each count type or visual comparison. Before requesting direct visual confirmation, navigate to and inspect the exact blocks, then put the External Agent's provisional assessment in context. This adds only a local Demo Session work item, contacts no one outside the Project Workspace, and needs no separate confirmation when the user requested Human Reviewer involvement.

Input schema

No input properties (empty object).

Raw JSON schema
{
  "type": "object",
  "anyOf": [
    {
      "additionalProperties": false,
      "type": "object",
      "required": [
        "question",
        "responseType",
        "documentId",
        "documentVersionId",
        "recommendedPageIds"
      ],
      "properties": {
        "question": {
          "minLength": 1,
          "maxLength": 240,
          "pattern": "\\S",
          "description": "One short request for exactly one judgment about one category or condition. For comparison or counting, name one exact type or item. Put background and provisional assessment in context.",
          "type": "string"
        },
        "context": {
          "minLength": 1,
          "maxLength": 2000,
          "pattern": "\\S",
          "description": "Optional evidence, expected or reference values, the External Agent's provisional visual assessment, and the exact uncertainty to confirm. Do not add another question or required action.",
          "type": "string"
        },
        "responseType": {
          "description": "Use point_set for one homogeneous set of marked locations. Every point has the same meaning and count is aggregate. Do not ask the Human Reviewer to classify points or mark multiple types; create separate requests. Use text for a plain-text response.",
          "const": "point_set",
          "type": "string"
        },
        "documentId": {
          "minLength": 1,
          "maxLength": 200,
          "description": "The immutable document ID on which a returned Point Set should be placed.",
          "type": "string"
        },
        "documentVersionId": {
          "minLength": 1,
          "maxLength": 200,
          "description": "The immutable document version on which a returned Point Set should be placed.",
          "type": "string"
        },
        "recommendedPageIds": {
          "maxItems": 25,
          "uniqueItems": true,
          "description": "Suggested starting pages for review, not a restriction on the response. For counting, include only non-overlapping source views where each physical instance appears once; do not combine plans and elevations.",
          "type": "array",
          "items": {
            "minLength": 1,
            "maxLength": 200,
            "description": "A suggested starting page ID in the Point Set target document.",
            "type": "string"
          }
        },
        "supportingDocumentReferences": {
          "minItems": 1,
          "maxItems": 10,
          "description": "Immutable document and page references that support the judgment, distinct from the Point Set target document.",
          "type": "array",
          "items": {
            "additionalProperties": false,
            "type": "object",
            "required": [
              "documentId",
              "documentVersionId",
              "pageIds"
            ],
            "properties": {
              "documentId": {
                "minLength": 1,
                "maxLength": 200,
                "description": "The immutable supporting evidence document ID.",
                "type": "string"
              },
              "documentVersionId": {
                "minLength": 1,
                "maxLength": 200,
                "description": "The immutable supporting evidence version paired with documentId.",
                "type": "string"
              },
              "pageIds": {
                "minItems": 1,
                "maxItems": 25,
                "uniqueItems": true,
                "description": "One to twenty-five page IDs in the supporting document version that support the judgment.",
                "type": "array",
                "items": {
                  "minLength": 1,
                  "maxLength": 200,
                  "description": "A page ID in the supporting document version.",
                  "type": "string"
                }
              }
            }
          }
        }
      }
    },
    {
      "additionalProperties": false,
      "type": "object",
      "required": [
        "question",
        "responseType"
      ],
      "properties": {
        "question": {
          "minLength": 1,
          "maxLength": 240,
          "pattern": "\\S",
          "description": "One short request for exactly one judgment about one category or condition. For comparison or counting, name one exact type or item. Put background and provisional assessment in context.",
          "type": "string"
        },
        "context": {
          "minLength": 1,
          "maxLength": 2000,
          "pattern": "\\S",
          "description": "Optional evidence, expected or reference values, the External Agent's provisional visual assessment, and the exact uncertainty to confirm. Do not add another question or required action.",
          "type": "string"
        },
        "responseType": {
          "description": "Use point_set for one homogeneous set of marked locations. Every point has the same meaning and count is aggregate. Do not ask the Human Reviewer to classify points or mark multiple types; create separate requests. Use text for a plain-text response.",
          "const": "text",
          "type": "string"
        }
      }
    }
  ]
}

Similar websites

econsor.de

econsor.de

German digital agency building portals, e-commerce sites and online marketing, combining strategy, design and AI to grow clients' visibility and customer base.

live Unverified Productivity & Business Transact tools
143 tools A0 / Act142 / T1 Not yet scored Seen 2026-11-05
econsor_click_search econsor_click_image econsor_click_menu econsor_click_burger_menu_icon econsor_click_previous_button
Inspect tools
inkframe-eta.vercel.app

inkframe-eta.vercel.app

Browser-native Elah video editor for 9:16 and 16:9 exports

live Unverified Productivity & Business Transact tools
87 tools A12 / Act71 / T4 Not yet scored Seen 2026-11-05
get_capabilities list_templates navigate_workspace open_template editor_inspect_video_moments
Inspect tools
agentdesk-demo.vercel.app

agentdesk-demo.vercel.app

Meridian Ops

live Unverified Productivity & Business Transact tools
83 tools A43 / Act24 / T16 Not yet scored Seen 2026-11-05
find_capabilities invoke_capability get_context get_action_status search_customers
Inspect tools
eworker.ca

eworker.ca

E-Worker is business infrastructure powered by AI, with focused apps and connected business work.

live Unverified Productivity & Business
73 tools A10 / Act63 / T0 Not yet scored Seen 2026-11-05
eworker_site_status eworker_list_apps eworker_resolve_app eworker_open_app ewdoc_status
Inspect tools

Related on Influzer