assemble_workspace

Inputs

{
  "type": "object",
  "properties": {
    "format": {
      "type": "string"
    },
    "topic": {
      "type": "string"
    },
    "hook_target": {
      "type": "string"
    },
    "your_channel": {
      "type": "string"
    },
    "n_examples": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 10
    },
    "workspace_id": {
      "type": "string"
    }
  },
  "additionalProperties": false,
  "required": []
}

Outputs and behavior

Select and rank saved examples for planning a video, with audience questions and available taste or own-channel context. Use to assemble a corpus slice; use get_workspace to read a saved workspace or critique_against_corpus to review a draft. Ranking uses format, performance tier and local engagement. Supplying workspace_id replaces that workspace's selected-item list; omitting it only returns the slice. Your agent performs any subsequent model analysis.

The registry does not publish an output schema for this tool. The description above is its documented behavior; response fields beyond it are not specified here.

Example call

Example tool name and arguments, generated from the input schema. Replace placeholder strings and sample numbers with your own values. This is a request template, not a recorded call or response.

{
  "name": "assemble_workspace",
  "arguments": {
    "workspace_id": "YOUR_WORKSPACE_ID",
    "n_examples": 10
  }
}

Clients

This tool is available to MCP clients using stdio or http.

The registry records transport support, not individual client test results. See the MCP setup reference for named clients, configuration, and tool-list limits.