Skip to main content
Glama

create_draft

Create a draft Substack post from markdown content without publishing. Converts markdown to Substack's format and saves as unpublished draft.

Instructions

Create a new draft post. Accepts markdown body which is converted to Substack's format. Does NOT publish — creates a draft only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesPost title
bodyNoPost body in markdown format
subtitleNoPost subtitle
audienceNoWho can see this posteveryone

Implementation Reference

  • Handler function for 'create_draft' tool. Converts markdown body to ProseMirror format, calls client.createDraft() with title, body, subtitle, and audience parameters, and returns the draft ID and title.
    async ({ title, body, subtitle, audience }) => {
      const prosemirrorBody = body ? markdownToProseMirror(body) : undefined;
      const draft = await client.createDraft(
        title,
        prosemirrorBody,
        subtitle,
        audience,
      );
      return {
        content: [
          {
            type: "text",
            text: JSON.stringify(
              {
                id: draft.id,
                title: draft.draft_title,
                message: "Draft created successfully. Open Substack to review and publish.",
              },
              null,
              2,
            ),
          },
        ],
      };
    },
  • Zod schema defining input parameters for 'create_draft' tool: title (required string), body (optional markdown), subtitle (optional string), and audience (optional enum with default 'everyone').
    {
      title: z.string().describe("Post title"),
      body: z.string().optional().describe("Post body in markdown format"),
      subtitle: z.string().optional().describe("Post subtitle"),
      audience: z
        .enum(["everyone", "only_paid", "founding", "only_free"])
        .optional()
        .default("everyone")
        .describe("Who can see this post"),
    },
  • src/server.ts:167-205 (registration)
    Registration of 'create_draft' tool with MCP server. Includes tool name, description, schema, and handler function.
    server.tool(
      "create_draft",
      "Create a new draft post. Accepts markdown body which is converted to Substack's format. Does NOT publish — creates a draft only.",
      {
        title: z.string().describe("Post title"),
        body: z.string().optional().describe("Post body in markdown format"),
        subtitle: z.string().optional().describe("Post subtitle"),
        audience: z
          .enum(["everyone", "only_paid", "founding", "only_free"])
          .optional()
          .default("everyone")
          .describe("Who can see this post"),
      },
      async ({ title, body, subtitle, audience }) => {
        const prosemirrorBody = body ? markdownToProseMirror(body) : undefined;
        const draft = await client.createDraft(
          title,
          prosemirrorBody,
          subtitle,
          audience,
        );
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(
                {
                  id: draft.id,
                  title: draft.draft_title,
                  message: "Draft created successfully. Open Substack to review and publish.",
                },
                null,
                2,
              ),
            },
          ],
        };
      },
    );
  • createDraft method in SubstackClient that constructs the API payload and makes POST request to /api/v1/drafts endpoint to create a new draft.
    async createDraft(
      title: string,
      body?: string,
      subtitle?: string,
      audience: string = "everyone",
    ): Promise<SubstackDraft> {
      const payload: DraftCreatePayload = {
        draft_title: title,
        draft_bylines: [{ id: this.userId, is_guest: false }],
        audience: audience as DraftCreatePayload["audience"],
        type: "newsletter",
      };
    
      if (subtitle) payload.draft_subtitle = subtitle;
      if (body) payload.draft_body = body;
    
      return this.request<SubstackDraft>(
        `${this.publicationUrl}/api/v1/drafts`,
        {
          method: "POST",
          body: JSON.stringify(payload),
        },
      );
    }
  • DraftCreatePayload interface defining the structure for creating drafts: draft_title, draft_subtitle, draft_body, draft_bylines, audience, type, and section_id.
    export interface DraftCreatePayload {
      draft_title: string;
      draft_subtitle?: string;
      draft_body?: string;
      draft_bylines: Array<{ id: number; is_guest: boolean }>;
      audience?: "everyone" | "only_paid" | "founding" | "only_free";
      type?: "newsletter" | "podcast" | "thread";
      section_id?: number | null;
    }
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context about markdown conversion and the draft-only nature, but doesn't cover other behavioral aspects like authentication requirements, error handling, rate limits, or what the tool returns. This is adequate but has clear gaps for a mutation tool.

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?

The description is extremely concise (two sentences) with zero wasted words. The first sentence states the core purpose, and the second adds crucial behavioral context. Every sentence earns its place, making it front-loaded and efficient.

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

Completeness3/5

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

Given this is a mutation tool with no annotations and no output schema, the description is minimally complete. It covers the basic purpose and key constraint (draft-only), but doesn't address return values, error conditions, or other contextual details that would be helpful for an agent. It's adequate but leaves gaps.

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 schema already fully documents all parameters. The description adds no additional parameter information beyond what's in the schema (e.g., it mentions 'markdown body' but the schema already describes 'body' as 'Post body in markdown format'). Baseline 3 is appropriate when the schema does all the work.

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?

The description clearly states the specific action ('Create a new draft post'), the resource ('draft post'), and distinguishes it from siblings by explicitly stating 'Does NOT publish — creates a draft only'. This differentiates it from publishing tools like 'update_draft' or 'list_published_posts'.

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 clear context about when to use this tool ('create a draft only') and implies when not to use it (for publishing). However, it doesn't explicitly name alternatives like 'update_draft' for modifying existing drafts or clarify when to use this versus 'create_note' tools, which prevents a perfect score.

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/conorbronsdon/substack-mcp'

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