Skip to main content
Glama

watch_mailbox

Monitor Gmail mailbox for email changes and send real-time notifications to a specified topic, with optional label-based filtering to focus on relevant messages.

Instructions

Watch for changes to the user's mailbox

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNameYesThe name of the Cloud Pub/Sub topic to publish notifications to
labelIdsNoLabel IDs to restrict notifications to
labelFilterActionNoWhether to include or exclude the specified labels

Implementation Reference

  • src/index.ts:1314-1327 (registration)
    Registration of the 'watch_mailbox' tool, including description, input schema, and inline handler function that uses the Gmail API to watch the mailbox for changes.
    server.tool("watch_mailbox",
      "Watch for changes to the user's mailbox",
      {
        topicName: z.string().describe("The name of the Cloud Pub/Sub topic to publish notifications to"),
        labelIds: z.array(z.string()).optional().describe("Label IDs to restrict notifications to"),
        labelFilterAction: z.enum(['include', 'exclude']).optional().describe("Whether to include or exclude the specified labels")
      },
      async (params) => {
        return handleTool(config, async (gmail: gmail_v1.Gmail) => {
          const { data } = await gmail.users.watch({ userId: 'me', requestBody: params })
          return formatResponse(data)
        })
      }
    )
  • The handler function for the watch_mailbox tool. It invokes handleTool which authenticates and calls the Gmail API's users.watch method to set up push notifications for mailbox changes.
    async (params) => {
      return handleTool(config, async (gmail: gmail_v1.Gmail) => {
        const { data } = await gmail.users.watch({ userId: 'me', requestBody: params })
        return formatResponse(data)
      })
    }
  • Zod input schema for the watch_mailbox tool, defining parameters: topicName (required string), labelIds (optional array of strings), labelFilterAction (optional enum: 'include' or 'exclude').
    {
      topicName: z.string().describe("The name of the Cloud Pub/Sub topic to publish notifications to"),
      labelIds: z.array(z.string()).optional().describe("Label IDs to restrict notifications to"),
      labelFilterAction: z.enum(['include', 'exclude']).optional().describe("Whether to include or exclude the specified labels")
    },
  • Shared helper function used by all tools, including watch_mailbox, to handle OAuth2 authentication, create Gmail client, execute the API call, and format errors.
    const handleTool = async (queryConfig: Record<string, any> | undefined, apiCall: (gmail: gmail_v1.Gmail) => Promise<any>) => {
      try {
        const oauth2Client = queryConfig ? createOAuth2Client(queryConfig) : defaultOAuth2Client
        if (!oauth2Client) throw new Error('OAuth2 client could not be created, please check your credentials')
    
        const credentialsAreValid = await validateCredentials(oauth2Client)
        if (!credentialsAreValid) throw new Error('OAuth2 credentials are invalid, please re-authenticate')
    
        const gmailClient = queryConfig ? google.gmail({ version: 'v1', auth: oauth2Client }) : defaultGmailClient
        if (!gmailClient) throw new Error('Gmail client could not be created, please check your credentials')
    
        const result = await apiCall(gmailClient)
        return result
      } catch (error: any) {
        // Check for specific authentication errors
        if (
          error.message?.includes("invalid_grant") ||
          error.message?.includes("refresh_token") ||
          error.message?.includes("invalid_client") ||
          error.message?.includes("unauthorized_client") ||
          error.code === 401 ||
          error.code === 403
        ) {
          return formatResponse({
            error: `Authentication failed: ${error.message}. Please re-authenticate by running: npx @shinzolabs/gmail-mcp auth`,
          });
        }
    
        return formatResponse({ error: `Tool execution failed: ${error.message}` });
      }
    }
Behavior2/5

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 states the tool watches for changes but lacks critical details: it doesn't specify that this creates a persistent subscription (implied by 'watch'), describe the notification format, mention authentication or permission requirements, indicate rate limits, or explain how to stop the watch (requiring stop_mail_watch). This leaves significant gaps for a monitoring 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 a single, clear sentence with zero wasted words, making it highly concise and front-loaded. It efficiently communicates the core purpose without unnecessary elaboration, earning a perfect score for this dimension.

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

Completeness2/5

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

Given the tool's complexity (persistent monitoring with external integration via Pub/Sub), lack of annotations, and no output schema, the description is insufficiently complete. It doesn't cover behavioral aspects like subscription lifecycle, error handling, or response format, leaving the agent with critical gaps in understanding how to use the tool effectively.

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 fully documents all three parameters (topicName, labelIds, labelFilterAction). The description adds no additional meaning beyond the schema's parameter descriptions, such as explaining how label filtering interacts with change detection or providing examples. The baseline score of 3 reflects adequate but minimal value added.

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

Purpose4/5

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

The description 'Watch for changes to the user's mailbox' clearly states the tool's purpose with a specific verb ('watch') and resource ('user's mailbox'), distinguishing it from siblings like list_messages or get_message that retrieve data rather than monitor changes. However, it doesn't explicitly differentiate from stop_mail_watch, which is its direct counterpart for ending the watch.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a Cloud Pub/Sub topic), compare it to stop_mail_watch for ending monitoring, or indicate scenarios where it's preferred over polling tools like list_messages for change detection.

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/faithk7/gmail-mcp'

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