Skip to main content
Glama

faf_guide

Guides users through FAF MCP usage for Claude Desktop, covering Projects conventions, path resolution, and UX patterns.

Instructions

FAF MCP usage guide for Claude Desktop - Projects convention, path resolution, and UX patterns

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The main handler function that returns a hardcoded guide string about FAF MCP usage conventions for Claude Desktop.
      private async handleFafGuide(_args: any): Promise<CallToolResult> {
        const guide = `# FAF MCP - Claude Desktop Guide
    
    ## Path Convention (CRITICAL)
    **Default**: \`~/Projects/[project-name]/project.faf\`
    
    **Project name from:**
    1. AI inference (README, files, context)
    2. User statement
    3. User custom path (always wins)
    
    **Example Flow:**
    - User uploads README for "Heritage Club Dubai"
    - Infer: \`~/Projects/heritage-club-dubai/project.faf\`
    - Confirm: "Creating at ~/Projects/heritage-club-dubai/"
    
    ## Real Filesystem Only
    - ✅ \`/Users/wolfejam/Projects/my-app/\`
    - ❌ \`/mnt/user-data/\` (container paths)
    - ❌ \`/home/claude/\` (container paths)
    
    ## Commands
    All work: \`faf init\`, \`faf init new\`, \`faf init --new\`, \`faf init -new\`
    
    **Core:**
    - \`faf init\` - create FAF (infer path from context)
    - \`faf score\` - show AI-readiness
    - \`faf sync\` - synchronize files
    - \`faf quick\` - rapid FAF creation
    
    **Extensions:**
    - \`new\` - force overwrite existing
    - \`full\` - detailed output
    - \`bi\` - bi-directional sync
    
    ## UX Rules
    1. **Don't offer option menus** - just solve it
    2. **Infer project name** from context
    3. **Suggest Projects path** if ambiguous
    4. **User path always wins**
    5. **No CLI talk** - you ARE the FAF system
    
    ## Quick Patterns
    
    **User uploads README:**
    → Infer project name
    → Create at \`~/Projects/[name]/project.faf\`
    → Confirm location
    
    **User gives path:**
    → Use exactly as provided
    → No validation needed
    
    **No context available:**
    → Ask once: "Project name or path?"
    → Use Projects convention with answer
    
    ## Username Detection
    - Check \`$HOME\` environment
    - Default to \`~/Projects/\` structure
    - Works across macOS/Linux/Windows
    
    ## Test Your Understanding
    ❌ "I need more information" (when README uploaded)
    ❌ "Option 1, Option 2, Option 3..." (option menus)
    ❌ Creating files in \`/mnt/user-data/\`
    ✅ "Creating FAF for [project] at ~/Projects/[name]/"
    ✅ Using context to infer and act
    ✅ Real filesystem paths only`;
    
        return {
          content: [{
            type: 'text',
            text: guide
          }]
        };
      }
  • Registration entry defining the tool name, description, and an empty input schema.
    {
      name: 'faf_guide',
      description: 'FAF MCP usage guide for Claude Desktop - Projects convention, path resolution, and UX patterns',
      inputSchema: {
        type: 'object',
        properties: {},
      }
  • Dispatch case in the tool handler switch statement that routes 'faf_guide' to handleFafGuide.
    case 'faf_guide':
      return await this.handleFafGuide(args);
Behavior2/5

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

No annotations provided, and the description does not disclose behavioral traits such as whether the tool is read-only, what it outputs, or any side effects. The absence of such information leaves the agent guessing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Single sentence but uses a dash to list topics, making it slightly awkward. Not overly long, but lacks clear structure or front-loading of key info.

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?

With no annotations, no output schema, and zero parameters, the description is minimal. A guide tool should at least indicate its output format or typical usage context (e.g., displays text on first use). Current description is insufficient.

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 tool has zero parameters and 100% schema description coverage. The description adds meaning by specifying the content domain (guide for Claude Desktop, specific topics), which compensates for the empty schema.

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 states it's a usage guide covering specific topics (Projects convention, path resolution, UX patterns), but lacks a clear verb or explicit statement of what the tool does (e.g., returns documentation text). The purpose is somewhat clear but not definitive.

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?

No guidance on when to use this tool versus its siblings (e.g., faf_about, faf_debug). No when-not conditions or alternatives mentioned.

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/Wolfe-Jam/grok-faf-mcp'

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