Skip to main content
Glama

list_drafts

Retrieve draft emails from your Gmail mailbox with options to filter by search query, limit results, and include spam/trash items.

Instructions

List drafts in the user's mailbox

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maxResultsNoMaximum number of drafts to return. Accepts values between 1-500
qNoOnly return drafts matching the specified query. Supports the same query format as the Gmail search box
includeSpamTrashNoInclude drafts 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

  • Handler function for the 'list_drafts' tool. Lists Gmail drafts using the Gmail API, handles pagination by fetching all pages until no nextPageToken, processes each draft's message payload (decoding bodies if applicable), and returns a formatted response.
    async (params) => {
      return handleTool(config, async (gmail: gmail_v1.Gmail) => {
        let drafts: Draft[] = []
    
        const { data } = await gmail.users.drafts.list({ userId: 'me', ...params })
    
        drafts.push(...data.drafts || [])
    
        while (data.nextPageToken) {
          const { data: nextData } = await gmail.users.drafts.list({ userId: 'me', ...params, pageToken: data.nextPageToken })
          drafts.push(...nextData.drafts || [])
        }
    
        if (drafts) {
          drafts = drafts.map(draft => {
            if (draft.message?.payload) {
              draft.message.payload = processMessagePart(
                draft.message.payload,
                params.includeBodyHtml
              )
            }
            return draft
          })
        }
    
        return formatResponse(drafts)
      })
    }
  • Zod schema defining the input parameters for the 'list_drafts' tool: maxResults, q (query), includeSpamTrash, includeBodyHtml.
    {
      maxResults: z.number().optional().describe("Maximum number of drafts to return. Accepts values between 1-500"),
      q: z.string().optional().describe("Only return drafts matching the specified query. Supports the same query format as the Gmail search box"),
      includeSpamTrash: z.boolean().optional().describe("Include drafts 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:333-369 (registration)
    MCP server registration of the 'list_drafts' tool, including description, input schema, and handler function reference.
    server.tool("list_drafts",
      "List drafts in the user's mailbox",
      {
        maxResults: z.number().optional().describe("Maximum number of drafts to return. Accepts values between 1-500"),
        q: z.string().optional().describe("Only return drafts matching the specified query. Supports the same query format as the Gmail search box"),
        includeSpamTrash: z.boolean().optional().describe("Include drafts 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) => {
          let drafts: Draft[] = []
    
          const { data } = await gmail.users.drafts.list({ userId: 'me', ...params })
    
          drafts.push(...data.drafts || [])
    
          while (data.nextPageToken) {
            const { data: nextData } = await gmail.users.drafts.list({ userId: 'me', ...params, pageToken: data.nextPageToken })
            drafts.push(...nextData.drafts || [])
          }
    
          if (drafts) {
            drafts = drafts.map(draft => {
              if (draft.message?.payload) {
                draft.message.payload = processMessagePart(
                  draft.message.payload,
                  params.includeBodyHtml
                )
              }
              return draft
            })
          }
    
          return formatResponse(drafts)
        })
      }
    )
  • Shared helper function used by all Gmail tools, including list_drafts. Handles OAuth2 client creation, credential validation, Gmail client instantiation, API call execution, and comprehensive error handling with specific auth error responses.
    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}` });
      }
    }
  • Recursive helper function to process Gmail message parts: decodes base64 bodies for text/plain and optionally text/html, processes nested parts, and filters headers to a predefined list. Used in list_drafts to prepare draft payloads.
    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
    }
Behavior2/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. While 'List drafts' implies a read-only operation, the description doesn't mention important behavioral aspects like pagination behavior, rate limits, authentication requirements, or what format the results will be in. For a tool with no annotation coverage, this leaves significant gaps in understanding how it behaves.

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 at just 5 words, front-loading the essential information with zero wasted words. Every word earns its place, making it easy to parse quickly while still conveying the core functionality.

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 lack of annotations and output schema, the description is insufficiently complete. For a tool that returns data (especially with multiple filtering parameters), the description should at least hint at what kind of data structure to expect or mention that results are filtered/paginated. The current description leaves too many open questions about how the tool behaves and what it returns.

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 description provides no parameter information, but the input schema has 100% description coverage with clear documentation for all 4 parameters. This meets the baseline score of 3 since the schema does the heavy lifting of explaining what each parameter does and their constraints. The description adds no value beyond what's already in the structured schema.

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') and resource ('drafts in the user's mailbox'), making the purpose immediately understandable. However, it doesn't differentiate this tool from similar sibling tools like 'list_messages' or 'list_threads', which would require mentioning it specifically returns draft messages rather than all messages or threads.

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. With sibling tools like 'list_messages' and 'get_draft' available, there's no indication whether this is the primary way to retrieve drafts or when to choose it over other listing/fetching tools. The description simply states what it does without context.

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