Skip to main content
Glama
launchnotes

LaunchNotes MCP Server

Official
by launchnotes

Create LaunchNotes Announcement

launchnotes_create_announcement

Create draft announcements in LaunchNotes projects to communicate updates, features, or releases with structured content formats.

Instructions

Create a new draft announcement in a LaunchNotes project. The announcement will be created in draft state.

Args:

  • project_id (string): The ID of the project

  • headline (string): The main headline/title (required)

  • content_markdown (string, optional): Content in Markdown format

  • content_html (string, optional): Content in HTML format

  • content_jira (string, optional): Content in Jira Wiki Syntax

Note: Provide only ONE content format. If multiple are provided, the API will use contentMarkdown > contentHtml > contentJira in order of precedence.

Returns: Created announcement with ID, headline, state, and creation timestamp

Use Cases:

  • "Create a new announcement about the API update"

  • "Draft an announcement for the new feature launch"

  • "Create announcement with headline 'v2.0 Released'"

Error Handling:

  • Returns validation errors if required fields are missing

  • Returns "Project not found" if project ID doesn't exist

  • Returns "Authentication failed" if API token lacks permission

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYesThe ID of the LaunchNotes project
headlineYesThe main headline/title of the announcement
content_markdownNoThe full content/body of the announcement in Markdown format
content_htmlNoThe full content/body of the announcement in HTML format
content_jiraNoThe full content/body of the announcement in Jira Wiki Syntax

Implementation Reference

  • Handler function that executes the tool: processes params, builds attributes from headline and content fields, calls createAnnouncement helper, handles GraphQL errors, returns success message with announcement details or error response.
    async (params: CreateAnnouncementInput) => {
      try {
        const attributes: Record<string, unknown> = {
          headline: params.headline,
        };
    
        if (params.content_markdown !== undefined)
          attributes.contentMarkdown = params.content_markdown;
        if (params.content_html !== undefined)
          attributes.contentHtml = params.content_html;
        if (params.content_jira !== undefined)
          attributes.contentJira = params.content_jira;
    
        const result = await createAnnouncement(client,
          params.project_id,
          attributes
        );
    
        if (
          result.createAnnouncement.errors &&
          result.createAnnouncement.errors.length > 0
        ) {
          const errorMessages = result.createAnnouncement.errors
            .map((err) => err.message)
            .join(", ");
          throw new Error(errorMessages);
        }
    
        const announcement = result.createAnnouncement.announcement;
    
        return {
          content: [
            {
              type: "text",
              text: `✓ Successfully created announcement "${announcement?.headline}"\n\n**ID:** ${announcement?.id}\n**State:** ${announcement?.state}\n**Created:** ${announcement?.createdAt}\n\nThe announcement has been created as a draft. Use the publish or schedule tool to make it live.`,
            },
          ],
        };
      } catch (error) {
        return {
          isError: true,
          content: [
            {
              type: "text",
              text: `Error creating announcement: ${error instanceof Error ? error.message : "Unknown error"}`,
            },
          ],
        };
      }
    }
  • Zod schema defining input validation for the tool parameters: project_id (required), headline (required), optional content in markdown/html/jira formats.
    export const CreateAnnouncementSchema = z
      .object({
        project_id: z
          .string()
          .min(1, "Project ID is required")
          .describe("The ID of the LaunchNotes project"),
        headline: z
          .string()
          .min(1, "Headline is required")
          .describe("The main headline/title of the announcement"),
        content_markdown: z
          .string()
          .optional()
          .describe("The full content/body of the announcement in Markdown format"),
        content_html: z
          .string()
          .optional()
          .describe("The full content/body of the announcement in HTML format"),
        content_jira: z
          .string()
          .optional()
          .describe("The full content/body of the announcement in Jira Wiki Syntax"),
      })
      .strict();
  • MCP server tool registration: defines name, title, description, input schema, annotations, and references the handler function.
      server.registerTool(
        "launchnotes_create_announcement",
        {
          title: "Create LaunchNotes Announcement",
          description: `Create a new draft announcement in a LaunchNotes project. The announcement will be created in draft state.
    
    Args:
      - project_id (string): The ID of the project
      - headline (string): The main headline/title (required)
      - content_markdown (string, optional): Content in Markdown format
      - content_html (string, optional): Content in HTML format
      - content_jira (string, optional): Content in Jira Wiki Syntax
    
    Note: Provide only ONE content format. If multiple are provided, the API will use contentMarkdown > contentHtml > contentJira in order of precedence.
    
    Returns:
      Created announcement with ID, headline, state, and creation timestamp
    
    Use Cases:
      - "Create a new announcement about the API update"
      - "Draft an announcement for the new feature launch"
      - "Create announcement with headline 'v2.0 Released'"
    
    Error Handling:
      - Returns validation errors if required fields are missing
      - Returns "Project not found" if project ID doesn't exist
      - Returns "Authentication failed" if API token lacks permission`,
          inputSchema: CreateAnnouncementSchema,
          annotations: {
            readOnlyHint: false,
            destructiveHint: false,
            idempotentHint: false,
            openWorldHint: true,
          },
        },
        async (params: CreateAnnouncementInput) => {
          try {
            const attributes: Record<string, unknown> = {
              headline: params.headline,
            };
    
            if (params.content_markdown !== undefined)
              attributes.contentMarkdown = params.content_markdown;
            if (params.content_html !== undefined)
              attributes.contentHtml = params.content_html;
            if (params.content_jira !== undefined)
              attributes.contentJira = params.content_jira;
    
            const result = await createAnnouncement(client,
              params.project_id,
              attributes
            );
    
            if (
              result.createAnnouncement.errors &&
              result.createAnnouncement.errors.length > 0
            ) {
              const errorMessages = result.createAnnouncement.errors
                .map((err) => err.message)
                .join(", ");
              throw new Error(errorMessages);
            }
    
            const announcement = result.createAnnouncement.announcement;
    
            return {
              content: [
                {
                  type: "text",
                  text: `✓ Successfully created announcement "${announcement?.headline}"\n\n**ID:** ${announcement?.id}\n**State:** ${announcement?.state}\n**Created:** ${announcement?.createdAt}\n\nThe announcement has been created as a draft. Use the publish or schedule tool to make it live.`,
                },
              ],
            };
          } catch (error) {
            return {
              isError: true,
              content: [
                {
                  type: "text",
                  text: `Error creating announcement: ${error instanceof Error ? error.message : "Unknown error"}`,
                },
              ],
            };
          }
        }
      );
  • Helper function that executes the GraphQL createAnnouncement mutation, building the input with projectId and attributes, returns the response with announcement or errors.
    export async function createAnnouncement(
      client: GraphQLClient,
      projectId: string,
      attributes: Record<string, unknown>
    ): Promise<{
      createAnnouncement: {
        announcement?: {
          id: string;
          headline: string;
          state: string;
          createdAt: string;
        };
        errors?: Array<{
          message: string;
          path?: string[];
        }>;
      };
    }> {
      return client.execute(CREATE_ANNOUNCEMENT_MUTATION, {
        input: {
          announcement: {
            projectId,
            ...attributes,
          },
        },
      });
    }
Behavior4/5

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

The description adds valuable behavioral context beyond annotations: it specifies the announcement is created in draft state (not published), explains the precedence order for content formats, and details error handling scenarios. While annotations cover basic safety (destructiveHint: false, readOnlyHint: false), the description provides practical implementation details that help the agent use the tool correctly.

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

Conciseness4/5

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

The description is well-structured with clear sections (Args, Note, Returns, Use Cases, Error Handling) and front-loads the core purpose. While comprehensive, some sections like the detailed error handling could be slightly more concise. Every sentence serves a purpose in guiding the agent.

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?

For a creation tool with no output schema, the description provides excellent context: it explains the draft state behavior, parameter relationships, return values, use cases, and error scenarios. The only minor gap is not explicitly mentioning the tool's relationship to sibling tools for workflow context, but overall it's highly complete.

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

Parameters4/5

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

With 100% schema description coverage, the baseline is 3. The description adds significant value by explaining the mutual exclusivity rule for content formats ('Provide only ONE content format') and the precedence order, which isn't captured in the schema. This compensates for the schema's limitation in expressing parameter relationships.

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 announcement'), resource ('in a LaunchNotes project'), and state ('in draft state'). It distinguishes from siblings like launchnotes_publish_announcement and launchnotes_update_announcement by specifying this creates a draft rather than publishing or updating existing announcements.

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 (creating draft announcements) and includes use case examples. However, it doesn't explicitly state when NOT to use it or name specific alternative tools from the sibling list for different scenarios like publishing or updating announcements.

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/launchnotes/mcp'

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