Skip to main content
Glama

list_destinations

Read-only

Shows available destinations like GitHub repos, Jira projects, and Linear teams where normalized ideas can be committed for implementation.

Instructions

List connected COMMIT destinations (GitHub repos, Jira projects, Linear teams).

These are where ideas become REAL. After normalizing an idea, show the user where they can commit it.

USE this tool when:

  • After normalize_idea, to show commit options

  • User asks "where can I commit?", "show my repos", "what's connected?"

  • User is ready to commit but needs to choose a destination

DO NOT use this tool when:

  • User is still exploring or drafting ideas (doesn't need destinations yet)

  • User is just using normalize_idea (show inline commit options instead)

This tool requires IdeaLift authentication. Normalizing ideas is free, committing requires connection.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The handleListDestinations function fetches and formats the user's connected commit destinations.
    export async function handleListDestinations(
      chatgptSubjectId?: string
    ): Promise<{ structuredContent: ListDestinationsResult; content: string }> {
      const idealiftUrl = process.env.IDEALIFT_APP_URL || 'https://idealift.app';
    
      if (!chatgptSubjectId) {
        return {
          structuredContent: {
            authenticated: false,
            destinations: [],
          },
          content: `## Connect IdeaLift First
    
    To see and use your ticket destinations, connect your IdeaLift account by re-adding the IdeaLift app in ChatGPT settings to trigger the OAuth flow.
    
    **In the meantime:** Use **normalize_idea** to structure your ideas - I'll save them for when you're connected!`,
        };
      }
    
      try {
        const result = await idealiftClient.listDestinations(chatgptSubjectId);
    
        if (!result.authenticated) {
          return {
            structuredContent: result,
            content: `## Connect IdeaLift First
    
    To see and use your ticket destinations, connect your IdeaLift account.
    
    **In the meantime:** Use **normalize_idea** to structure your ideas!`,
          };
        }
    
        const connected = result.destinations.filter(d => d.connected);
        if (connected.length === 0) {
          return {
            structuredContent: result,
            content: `## No Commit Destinations Yet
    
    You're connected to **${result.workspaceName}**, but haven't connected anywhere to commit ideas.
    
    **Connect a destination to start committing:**
    - **GitHub** - Commit ideas as GitHub issues
    - **Jira** - Commit ideas as Jira tickets
    - **Linear** - Commit ideas as Linear issues
    
    Just say "connect GitHub" (or Jira/Linear) and I'll walk you through it!`,
          };
        }
    
        // Build a nice table of destinations
        const destLines = connected.map(d => {
          const icon = d.type === 'github' ? '🐙' : d.type === 'jira' ? '🔷' : '📐';
          const defaultBadge = d.default ? ' *(default)*' : '';
          const config = d.config?.repo || d.config?.projectKey || d.config?.teamId || '';
          return `| ${icon} ${d.type.charAt(0).toUpperCase() + d.type.slice(1)} | ${d.name} | ${config}${defaultBadge} |`;
        });
    
        return {
          structuredContent: result,
          content: `## Your Commit Destinations
    
    | Service | Name | Details |
    |---------|------|---------|
    ${destLines.join('\n')}
    
    **Ready to commit?** Just say "commit to GitHub" (or Jira/Linear), or I'll use your default.
    
    **Need to connect more?** Say "connect GitHub" (or Jira/Linear).`,
        };
      } catch (error) {
        console.error('List destinations error:', error);
    
        return {
          structuredContent: {
            authenticated: false,
            destinations: [],
          },
          content: `## Couldn't Load Destinations
    
    There was an issue loading your destinations. This might be temporary.
    
    **Try:** Say "check my connection" to verify your IdeaLift status.`,
        };
      }
    }
  • The ListDestinationsResult interface defines the expected output structure for the list_destinations tool.
    export interface ListDestinationsResult {
      authenticated: boolean;
      workspaceName?: string;
      destinations: Destination[];
      authUrl?: string;
    }
  • The listDestinationsTool object defines the MCP tool registration details for 'list_destinations'.
    export const listDestinationsTool = {
      name: 'list_destinations',
      description: `List connected COMMIT destinations (GitHub repos, Jira projects, Linear teams).
    
    These are where ideas become REAL. After normalizing an idea, show the user where they can commit it.
    
    USE this tool when:
    - After normalize_idea, to show commit options
    - User asks "where can I commit?", "show my repos", "what's connected?"
    - User is ready to commit but needs to choose a destination
    
    DO NOT use this tool when:
    - User is still exploring or drafting ideas (doesn't need destinations yet)
    - User is just using normalize_idea (show inline commit options instead)
    
    This tool requires IdeaLift authentication. Normalizing ideas is free, committing requires connection.`,
      inputSchema: {
        type: 'object' as const,
        properties: {},
        required: [],
      },
      annotations: {
        readOnlyHint: true,     // Pure read operation - only fetches and returns connected destinations
        destructiveHint: false, // Read-only query, no data modification
        openWorldHint: true,    // Calls IdeaLift API to fetch destinations
      },
      _meta: {
        'openai/visibility': 'public',
      },
    };
Behavior4/5

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

Annotations establish the read-only, non-destructive safety profile. The description adds critical behavioral context absent from annotations: authentication requirements ('requires IdeaLift authentication'), cost model ('Normalizing ideas is free, committing requires connection'), and workflow integration ('After normalizing an idea...'). Minor gap on error states or empty result handling.

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?

Excellent structural organization with clear visual hierarchy: purpose summary → value proposition → explicit usage conditions → authentication note. Every sentence earns its place; no redundancy or tautology. The front-loading of purpose before guidelines allows quick scanning.

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

Completeness4/5

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

For a parameter-less read operation with annotations covering safety, the description is highly complete. It compensates for the missing output schema by enumerating destination types (GitHub, Jira, Linear). Minor deduction for not explicitly describing the return structure format, though the enumerated examples provide sufficient inference.

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?

With zero parameters in the input schema, the baseline score applies. The description correctly assumes no parameter explanation is needed, focusing instead on contextual usage guidance.

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 opens with a specific verb ('List') and resource ('connected COMMIT destinations'), immediately clarifying scope. It distinguishes the resource type with concrete examples (GitHub repos, Jira projects, Linear teams), making it unambiguous what this tool retrieves compared to siblings like 'list_ideas' or 'list_signals'.

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

Usage Guidelines5/5

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

Explicit 'USE this tool when' and 'DO NOT use this tool when' sections provide clear workflow boundaries. It specifically references sibling tool 'normalize_idea' as both a prerequisite trigger and an alternative to inline options, directly addressing when to invoke vs. when to skip. This is exemplary guidance.

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/Startvest-LLC/idealift-mcp-server'

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