Skip to main content
Glama
lindoai

mcp-lindoai

Official

Create Page

create_page

Create a page on an existing website using AI. Initiates an async workflow and returns an ID to track progress via status checks.

Instructions

Create a new page on an existing website using AI. Starts an asynchronous workflow and returns a workflow_id immediately — poll check_page_status with that id to track progress and get the final result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
website_idYesThe website ID
promptYesDescribe the page to create
schedule_atNoOptional ISO 8601 datetime to schedule for later

Implementation Reference

  • The tool 'create_page' is registered using server.registerTool() with title 'Create Page', description explaining it starts an async workflow, and inputSchema requiring website_id and prompt, with an optional schedule_at.
    server.registerTool(
      "create_page",
      {
        title: "Create Page",
        description: "Create a new page on an existing website using AI. Starts an asynchronous workflow and returns a `workflow_id` immediately — poll `check_page_status` with that id to track progress and get the final result.",
        inputSchema: {
        website_id: z.string().describe("The website ID"),
        prompt: z.string().describe("Describe the page to create"),
        schedule_at: z.string().optional().describe("Optional ISO 8601 datetime to schedule for later"),
      },
        annotations: { readOnlyHint: false, destructiveHint: false, openWorldHint: true },
      },
      async ({ website_id, prompt, schedule_at }) => {
        const body = { prompt };
        if (schedule_at) body.schedule_at = schedule_at;
        const data = await apiCall(`/v1/ai/workspace/website/${website_id}/page`, "POST", body);
        const payload = data?.result || data;
        return { content: [{ type: "text", text: JSON.stringify(payload, null, 2) }] };
      }
    );
  • Handler function that executes the tool logic: builds a body with prompt (and optionally schedule_at), calls POST /v1/ai/workspace/website/{website_id}/page, and returns the result as text content.
    async ({ website_id, prompt, schedule_at }) => {
      const body = { prompt };
      if (schedule_at) body.schedule_at = schedule_at;
      const data = await apiCall(`/v1/ai/workspace/website/${website_id}/page`, "POST", body);
      const payload = data?.result || data;
      return { content: [{ type: "text", text: JSON.stringify(payload, null, 2) }] };
    }
  • Input schema using zod: website_id (string), prompt (string), and optional schedule_at (ISO 8601 string).
      website_id: z.string().describe("The website ID"),
      prompt: z.string().describe("Describe the page to create"),
      schedule_at: z.string().optional().describe("Optional ISO 8601 datetime to schedule for later"),
    },
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the async behavior (starts workflow, returns id) which is not captured by annotations. Annotations indicate non-read-only (readOnlyHint=false) and non-destructive (destructiveHint=false), which is consistent. The openWorldHint=true is left unexplained but the description adds sufficient behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states purpose, second explains async flow and polling. Every sentence is necessary and front-loaded. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the set of sibling tools and no output schema, the description is complete. It covers the creation action and the async follow-up. Could mention error handling or cancellation, but not essential for basic usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add extra meaning beyond what the schema already provides (e.g., format for schedule_at). It merely restates prompt purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Create a new page on an existing website using AI', specifying the action (create), resource (page), and context (existing website). It distinguishes from siblings like create_blog or create_website.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: it is asynchronous, returns a workflow_id, and instructs to poll check_page_status for progress. This tells the agent how to use the tool effectively, though it does not mention alternatives or cases when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lindoai/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server