Skip to main content
Glama
ttommyth

Interactive MCP

message_complete_notification

Signal completion of tasks or responses by sending cross-platform notifications to users. Use this tool once per message to indicate when work is finished.

Instructions

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectNameYesNotification title
messageYesNotification body

Implementation Reference

  • The handler function for the 'message_complete_notification' tool. It extracts projectName and message from input args, sends a desktop notification using node-notifier, and returns a confirmation message.
    (args) => {
      // Use inferred args type
      const { projectName, message } = args;
      notifier.notify({ title: projectName, message });
      return {
        content: [
          {
            type: 'text',
            text: 'Notification sent. You can now wait for user input.',
          },
        ],
      };
    },
  • src/index.ts:153-176 (registration)
    The registration of the tool handler using server.tool(), conditionally based on tool enablement. Includes dynamic description resolution and schema from the tool definition.
    if (isToolEnabled('message_complete_notification')) {
      // Use properties from the imported tool object
      server.tool(
        'message_complete_notification',
        // Description is a string here, but handle consistently
        typeof messageCompleteNotificationTool.description === 'function'
          ? messageCompleteNotificationTool.description(globalTimeoutSeconds) // Should not happen based on definition, but safe
          : messageCompleteNotificationTool.description,
        messageCompleteNotificationTool.schema, // Use schema property
        (args) => {
          // Use inferred args type
          const { projectName, message } = args;
          notifier.notify({ title: projectName, message });
          return {
            content: [
              {
                type: 'text',
                text: 'Notification sent. You can now wait for user input.',
              },
            ],
          };
        },
      );
    }
  • Zod schema (raw shape) defining the input parameters: projectName and message, used for validation in the tool registration.
    const rawSchema: ZodRawShape = {
      projectName: z.string().describe('Notification title'),
      message: z.string().describe('Notification body'),
    };
  • JSON Schema in ToolCapabilityInfo defining the tool's parameters and description for MCP protocol capability declaration.
    const capabilityInfo: ToolCapabilityInfo = {
      description: 'Notify when a response has completed via OS notification.',
      parameters: {
        type: 'object',
        properties: {
          projectName: {
            type: 'string',
            description:
              'Identifies the context/project making the notification (appears in notification title)',
          },
          message: {
            type: 'string',
            description: 'The specific notification text (appears in the body)',
          },
        },
        required: ['projectName', 'message'],
      },
    };
  • Export of the ToolDefinition object combining capability, description, and schema, imported and used in index.ts for registration.
    export const messageCompleteNotificationTool: ToolDefinition = {
      capability: capabilityInfo,
      description: registrationDescription,
      schema: rawSchema, // Use the raw shape here
    };
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It effectively discloses key behavioral traits: the tool triggers cross-platform OS notifications, is mandatory and reusable, and must be called exactly once per LLM response. However, it lacks details on potential side effects (e.g., notification persistence, user interaction with notifications) or error handling, which could enhance transparency further.

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

Conciseness3/5

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

The description is structured with sections like <importantNotes> and <whenToUseThisTool>, which aids readability but adds verbosity. Some sections (e.g., <features> and <bestPractices>) include redundant or marginally useful information (e.g., 'Keep messages concise'), reducing efficiency. It is front-loaded with the core purpose, but could be more streamlined without losing clarity.

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 tool's moderate complexity (2 parameters, no output schema, no annotations), the description is largely complete: it covers purpose, usage, parameters, and examples. However, it lacks details on the notification behavior (e.g., how notifications are displayed, timeout settings) and error scenarios, which would be helpful for full contextual understanding despite the absence of an output schema.

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?

Schema description coverage is 100%, providing a baseline of 3. The description adds meaningful context beyond the schema: it explains that projectName 'identifies the context/project making the notification' and appears in the title, while message is 'the specific notification text' in the body. This clarifies the semantic role of each parameter, though it doesn't add syntax or format details beyond what the schema already covers.

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 explicitly states the tool's purpose: 'Notify when a response has completed' and 'signal completion to the user.' It distinguishes itself from sibling tools (like ask_intensive_chat or request_user_input) by focusing on notification signaling rather than interactive communication. The verb 'notify' and resource 'completion' are specific and clear.

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

Usage Guidelines5/5

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

The description provides explicit, detailed guidance on when to use this tool: 'once at the end of each and every message,' 'when you've completed answering a user's query,' 'when you've finished executing a task,' etc. It also specifies when NOT to use it (e.g., not multiple times per message) and distinguishes it from sibling tools by its notification-focused role, with clear alternatives implied (e.g., use other tools for ongoing interactions).

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/ttommyth/interactive-mcp'

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