Skip to main content
Glama

list_messages

Retrieve and filter email messages from your Gmail inbox using search queries, labels, and pagination controls to manage your mailbox efficiently.

Instructions

List messages in the user's mailbox with optional filtering

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maxResultsNoMaximum number of messages to return. Accepts values between 1-500
pageTokenNoPage token to retrieve a specific page of results
qNoOnly return messages matching the specified query. Supports the same query format as the Gmail search box
labelIdsNoOnly return messages with labels that match all of the specified label IDs
includeSpamTrashNoInclude messages from SPAM and TRASH in the results
includeBodyHtmlNoWhether to include the parsed HTML in the return for each body, excluded by default because they can be excessively large

Implementation Reference

  • The handler function for the 'list_messages' tool. It invokes the Gmail API's users.messages.list method with user-provided parameters, processes each message's payload by decoding bodies and filtering headers if applicable, and returns a formatted JSON response.
    async (params) => {
      return handleTool(config, async (gmail: gmail_v1.Gmail) => {
        const { data } = await gmail.users.messages.list({ userId: 'me', ...params })
    
        if (data.messages) {
          data.messages = data.messages.map((message: Message) => {
            if (message.payload) {
              message.payload = processMessagePart(
                message.payload,
                params.includeBodyHtml
              )
            }
            return message
          })
        }
    
        return formatResponse(data)
      })
    }
  • The Zod input schema for the 'list_messages' tool, defining optional parameters for pagination, querying, filtering by labels, including spam/trash, and body processing options.
    {
      maxResults: z.number().optional().describe("Maximum number of messages to return. Accepts values between 1-500"),
      pageToken: z.string().optional().describe("Page token to retrieve a specific page of results"),
      q: z.string().optional().describe("Only return messages matching the specified query. Supports the same query format as the Gmail search box"),
      labelIds: z.array(z.string()).optional().describe("Only return messages with labels that match all of the specified label IDs"),
      includeSpamTrash: z.boolean().optional().describe("Include messages from SPAM and TRASH in the results"),
      includeBodyHtml: z.boolean().optional().describe("Whether to include the parsed HTML in the return for each body, excluded by default because they can be excessively large"),
    },
  • src/index.ts:561-590 (registration)
    The registration of the 'list_messages' tool on the MCP server using server.tool(), specifying name, description, schema, and handler.
    server.tool("list_messages",
      "List messages in the user's mailbox with optional filtering",
      {
        maxResults: z.number().optional().describe("Maximum number of messages to return. Accepts values between 1-500"),
        pageToken: z.string().optional().describe("Page token to retrieve a specific page of results"),
        q: z.string().optional().describe("Only return messages matching the specified query. Supports the same query format as the Gmail search box"),
        labelIds: z.array(z.string()).optional().describe("Only return messages with labels that match all of the specified label IDs"),
        includeSpamTrash: z.boolean().optional().describe("Include messages from SPAM and TRASH in the results"),
        includeBodyHtml: z.boolean().optional().describe("Whether to include the parsed HTML in the return for each body, excluded by default because they can be excessively large"),
      },
      async (params) => {
        return handleTool(config, async (gmail: gmail_v1.Gmail) => {
          const { data } = await gmail.users.messages.list({ userId: 'me', ...params })
    
          if (data.messages) {
            data.messages = data.messages.map((message: Message) => {
              if (message.payload) {
                message.payload = processMessagePart(
                  message.payload,
                  params.includeBodyHtml
                )
              }
              return message
            })
          }
    
          return formatResponse(data)
        })
      }
    )
  • Helper function used in the handler to recursively process message parts: decodes base64 data to UTF-8 for text bodies (plain and optionally HTML), recurses on multipart, and filters headers to a predefined list.
    const processMessagePart = (messagePart: MessagePart, includeBodyHtml = false): MessagePart => {
      if ((messagePart.mimeType !== 'text/html' || includeBodyHtml) && messagePart.body) {
        messagePart.body = decodedBody(messagePart.body)
      }
    
      if (messagePart.parts) {
        messagePart.parts = messagePart.parts.map(part => processMessagePart(part, includeBodyHtml))
      }
    
      if (messagePart.headers) {
        messagePart.headers = messagePart.headers.filter(header => RESPONSE_HEADERS_LIST.includes(header.name || ''))
      }
    
      return messagePart
    }
  • Shared helper function used by the handler (and other tools) to manage OAuth2 authentication, validate credentials, create Gmail client, execute the API call, and handle 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) {
        return `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 full burden for behavioral disclosure. While 'List messages' implies a read operation, the description fails to mention critical behavioral aspects like pagination behavior (implied by pageToken parameter but not explained), rate limits, authentication requirements, whether results are sorted, or what happens when no messages match filters. The mention of 'optional filtering' is too vague to provide meaningful 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.

Conciseness4/5

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

The description is a single, efficient sentence that gets straight to the point without unnecessary words. It's appropriately sized for a list operation with filtering capabilities. However, it could be slightly more structured by explicitly mentioning the core action first, then the filtering capability.

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?

For a tool with 6 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what the tool returns (message objects, metadata only, etc.), doesn't mention pagination behavior despite having a pageToken parameter, and provides no context about performance implications (especially regarding the includeBodyHtml parameter's warning about excessive size). The description leaves too many open questions for effective agent use.

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?

The schema description coverage is 100%, providing complete documentation for all 6 parameters. The description adds minimal value beyond the schema - it mentions 'optional filtering' which aligns with parameters like 'q' and 'labelIds', but doesn't provide additional semantic context about how these filters interact or typical use patterns. This meets the baseline 3 when schema coverage is high.

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 clearly states the action ('List messages') and target ('in the user's mailbox'), providing a specific verb+resource combination. However, it doesn't distinguish this tool from similar sibling tools like 'list_drafts', 'list_threads', or 'get_message', which all involve retrieving message-related data from the same mailbox context.

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 mentions 'optional filtering' which implies some usage context, but provides no explicit guidance about when to use this tool versus alternatives like 'list_drafts', 'list_threads', or 'get_message'. There's no mention of prerequisites, performance considerations, or typical use cases that would help an agent choose between similar retrieval tools.

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/HitmanLy007/gmail-mcp'

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