Skip to main content
Glama

summarize_inbox

Summarize recent emails in your Outlook inbox to quickly review key messages without reading each one individually.

Instructions

Summarize inbox emails

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoNumber of emails to summarize

Implementation Reference

  • Defines the input schema, description, and registration of the 'summarize_inbox' tool in the list of available tools.
    {
      name: "summarize_inbox",
      description: "Summarize inbox emails",
      inputSchema: {
        type: "object",
        properties: {
          count: {
            type: "number",
            description: "Number of emails to summarize",
            default: 10
          }
        }
      }
    },
  • The handler function for 'summarize_inbox' tool. It retrieves the specified number (default 10) of inbox emails using OutlookManager, calculates the number of unread emails, and returns a formatted markdown text summary including totals and details of the top 5 recent emails.
    case 'summarize_inbox': {
      const count = (args as any)?.count || 10;
      const emails = await outlookManager.getInboxEmails(count);
      const unreadCount = emails.filter(e => !e.isRead).length;
      
      return {
        content: [
          {
            type: 'text',
            text: `šŸ“Š **Inbox Summary**\nTotal: ${emails.length} emails\nUnread: ${unreadCount} emails\n\nšŸ“‹ **Recent Emails:**\n` +
                 emails.slice(0, 5).map((email, index) => 
                   `${index + 1}. ${email.isRead ? 'āœ…' : 'šŸ“©'} **${email.subject}**\n   From: ${email.sender}\n   Time: ${email.receivedTime}\n`
                 ).join('\n')
          },
        ],
      };
    }
  • Alternative handler in index_new.js that delegates the summarization logic to EmailSummarizer.summarizeInbox after fetching emails.
    case 'summarize_inbox': {
        const emails = await outlookManager.getInboxEmails(args.count || 10);
        const summary = EmailSummarizer.summarizeInbox(emails);
        return {
            content: [
                {
                    type: 'text',
                    text: summary,
                },
            ],
        };
  • Likely the core summarization logic used by index_new.js (possibly called as summarizeInbox), which generates per-email summaries with priority detection, action flags, previews, and formats a multiple-email overview with stats on unread, high-priority, and action-required counts.
    static summarizeMultipleEmails(emails) {
        const summaries = emails.map(email => ({
            id: email.id,
            subject: email.subject,
            sender: email.sender,
            receivedTime: email.receivedTime,
            isRead: email.isRead,
            priority: this.detectPriority(email.subject, email.body),
            actionRequired: this.detectActionRequired(email.body),
            bodyPreview: this.extractBodyPreview(email.body)
        }));
        return this.formatMultipleSummaries(summaries);
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Summarize inbox emails' implies a read-only operation that processes multiple emails, but it doesn't specify what 'summarize' entails (e.g., format, length, content focus), whether it requires authentication, or if there are rate limits. For a tool with no annotation coverage, this leaves significant behavioral gaps.

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 with just three words, making it front-loaded and efficient. Every word ('Summarize inbox emails') directly contributes to understanding the tool's purpose without any wasted text. This is appropriately sized for a simple tool.

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 complexity (summarization of multiple emails), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what the summarization returns (e.g., a list of summaries, a single aggregated summary), how emails are selected (e.g., most recent), or any constraints. For a tool with no structured behavioral or output information, the description should provide more context.

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 input schema has 100% description coverage, with the single parameter 'count' clearly documented as 'Number of emails to summarize' with a default of 10. The description doesn't add any meaning beyond what the schema provides (e.g., it doesn't explain how 'count' interacts with inbox size or ordering). With high schema coverage, the baseline score of 3 is appropriate.

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

Purpose3/5

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

The description 'Summarize inbox emails' clearly states the verb ('summarize') and resource ('inbox emails'), making the basic purpose understandable. However, it doesn't distinguish this tool from its sibling 'summarize_email' (which appears to summarize individual emails) or 'get_inbox_emails' (which likely retrieves inbox emails without summarization). The purpose is clear but lacks sibling differentiation.

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 when this summarization is appropriate compared to retrieving raw emails with 'get_inbox_emails' or summarizing individual emails with 'summarize_email'. There's also no indication of prerequisites, limitations, or context for usage.

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/cqyefeng119/windows-outlook-mcp'

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