Skip to main content
Glama

vibe_inbox

Read-onlyIdempotent

Check unread messages and recent threads to stay updated on developer conversations.

Instructions

See your unread messages and recent threads.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Handler function for vibe_inbox - fetches inbox from store, sorts by unread first then recency, and returns formatted display of unread messages or 'all caught up' message.
    async function handler(args) {
      const initCheck = requireInit();
      if (initCheck) return initCheck;
    
      const myHandle = config.getHandle();
      const threads = await store.getInbox(myHandle);
    
      // Check for notifications (will handle deduplication internally)
      notify.checkAll(store);
    
      if (!threads || threads.length === 0) {
        return {
          display: `No messages yet. Say "dm @someone" to start a conversation.`
        };
      }
    
      // Sort: unread first, then by most recent
      const sorted = threads.sort((a, b) => {
        if (a.unread > 0 && b.unread === 0) return -1;
        if (b.unread > 0 && a.unread === 0) return 1;
        return (b.lastTimestamp || 0) - (a.lastTimestamp || 0);
      });
    
      const totalUnread = sorted.reduce((sum, t) => sum + (t.unread || 0), 0);
      const unreadSenders = sorted.filter(t => t.unread > 0);
    
      if (totalUnread === 0) {
        const recentHandles = sorted.slice(0, 3).map(t => `@${t.handle}`).join(', ');
        return {
          display: `All caught up. Recent: ${recentHandles}`
        };
      }
    
      // Build display
      let display = `📬 ${totalUnread} unread\n`;
      display += '───────────────────────────────────\n';
    
      for (const t of unreadSenders) {
        const preview = truncate(t.lastMessage || '', 60);
        display += `**@${t.handle}** (${t.unread}) — ${preview}\n`;
      }
    
      return { display };
    }
  • Input schema/definition for vibe_inbox - accepts no parameters, just describes it as 'See your unread messages and recent threads.'
    const definition = {
      name: 'vibe_inbox',
      description: 'See your unread messages and recent threads.',
      inputSchema: {
        type: 'object',
        properties: {}
      }
    };
  • index.js:164-175 (registration)
    Tool registration in the main index.js - vibe_inbox is loaded from ./tools/inbox and registered as part of the tools object.
    // Load GTM tools (8 core + init)
    const tools = {
      vibe_start: require('./tools/start'),
      vibe_init: require('./tools/init'),
      vibe_who: require('./tools/who'),
      vibe_dm: require('./tools/dm'),
      vibe_inbox: require('./tools/inbox'),
      vibe_status: require('./tools/status'),
      vibe_ship: require('./tools/ship'),
      vibe_discover: require('./tools/discover'),
      vibe_help: require('./tools/help'),
    };
  • index.js:27-38 (registration)
    Safety annotations registration for vibe_inbox - declared as readOnlyHint: true (read-only), idempotentHint: true (safe to repeat), openWorldHint: true (network access).
    const TOOL_ANNOTATIONS = {
      // ── GTM: 9 tools (8 core + init) ────────────────────────────
      vibe_start:    { readOnlyHint: false, destructiveHint: false, idempotentHint: false, openWorldHint: true },
      vibe_init:     { readOnlyHint: false, destructiveHint: false, idempotentHint: true,  openWorldHint: true },
      vibe_who:      { readOnlyHint: true,  destructiveHint: false, idempotentHint: true,  openWorldHint: true },
      vibe_dm:       { readOnlyHint: false, destructiveHint: false, idempotentHint: false, openWorldHint: true },
      vibe_inbox:    { readOnlyHint: true,  destructiveHint: false, idempotentHint: true,  openWorldHint: true },
      vibe_status:   { readOnlyHint: false, destructiveHint: false, idempotentHint: true,  openWorldHint: true },
      vibe_ship:     { readOnlyHint: false, destructiveHint: false, idempotentHint: false, openWorldHint: true },
      vibe_discover: { readOnlyHint: true,  destructiveHint: false, idempotentHint: true,  openWorldHint: true },
      vibe_help:     { readOnlyHint: true,  destructiveHint: false, idempotentHint: true,  openWorldHint: false },
    };
  • Proactive intelligence helper - vibe_inbox is listed as a social tool that triggers proactive suggestions when called.
    async function checkProactiveOpportunities(toolName, args = {}) {
      // Track away/back transitions
      if (toolName === 'vibe_away') {
        markAway();
      } else if (toolName === 'vibe_back') {
        // Don't mark back yet - let ships_in_the_night process
      } else if (toolName === 'vibe_init' || toolName === 'vibe_start') {
        setSessionStart();
      }
    
      // Only generate suggestions for certain tools
      const socialTools = ['vibe_who', 'vibe_inbox', 'vibe_start'];
      if (!socialTools.includes(toolName)) {
        return null;
      }
    
      return await getProactiveSummary(args);
    }
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is clear. The description adds the detail of returning 'unread messages and recent threads', but does not elaborate on behavior such as pagination or sorting. This is adequate but not enhanced beyond annotations.

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, concise sentence with no unnecessary words. It effectively communicates the core purpose without extraneous information.

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

Completeness3/5

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

Given the tool has no parameters, annotations are present, and no output schema is defined, the description is minimal but functional. However, it lacks details about the return format, ordering, or scope (e.g., how recent is 'recent'). For a simple tool this might suffice, but more context could improve usability.

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?

The input schema has zero parameters, so schema coverage is 100%. The description does not need to add parameter details. Per guidelines, baseline 4 applies when there are no parameters.

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 uses a clear verb ('see') and specifies the resource ('your unread messages and recent threads'), which accurately describes the tool's function. It distinguishes from siblings like vibe_dm (direct messages) and vibe_status (status updates) by focusing on the inbox concept.

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 like vibe_dm or vibe_discover. It does not mention scenarios, prerequisites, or exclusions, leaving the agent to infer usage 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/VibeCodingInc/vibe-mcp'

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