Skip to main content
Glama

vybsly_ask

Ask a question and receive a synthesized answer with cited source URLs for verification.

Instructions

Ask a question, get a sourced AI answer (like Perplexity). Returns a synthesized answer plus the source URLs used.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYesThe question to answer
max_sourcesNoHow many sources to cite (default 5)

Implementation Reference

  • Tool schema definition for 'vybsly_ask' — declares the tool name, description ('Perplexity-style sourced AI answer'), inputSchema requiring 'question' (string) with optional 'max_sources' (number, default 5).
      name: 'vybsly_ask',
      description: 'Ask a question, get a sourced AI answer (like Perplexity). Returns a synthesized answer plus the source URLs used.',
      inputSchema: {
        type: 'object',
        properties: {
          question: { type: 'string', description: 'The question to answer' },
          max_sources: { type: 'number', description: 'How many sources to cite (default 5)', default: 5 }
        },
        required: ['question']
      }
    },
  • index.js:34-35 (registration)
    The TOOLS array (line 34) that contains all tool definitions including 'vybsly_ask', registered on the server via ListToolsRequestSchema handler at line 417.
    const TOOLS = [
      {
  • Handler logic for 'vybsly_ask' — sends a POST request to `${VYBSLY_BASE}/ask` with JSON body containing 'question' and 'max_sources', then parses the JSON response. Unlike other tools (which use the shared vybslyCall helper), this one uses fetch directly for a POST request.
    case 'vybsly_ask': {
      const res = await fetch(`${VYBSLY_BASE}/ask`, {
        method: 'POST',
        headers: { 'Content-Type': 'application/json', ...(API_KEY && { 'X-API-Key': API_KEY }) },
        body: JSON.stringify({ question: args.question, max_sources: args.max_sources || 5 })
      });
      result = await res.json();
      break;
    }
  • index.js:417-417 (registration)
    The ListToolsRequestSchema handler that registers all TOOLS (including vybsly_ask) with the MCP server.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools: TOOLS }));
  • The vybslyCall helper function used by most tools; notably, 'vybsly_ask' does NOT use this helper (it uses raw fetch for POST), but this is the generic API helper for reference.
    async function vybslyCall(path, params = {}) {
      const qs = new URLSearchParams(params).toString();
      const url = `${VYBSLY_BASE}${path}${qs ? '?' + qs : ''}`;
      const headers = { 'Accept': 'application/json' };
      if (API_KEY) headers['X-API-Key'] = API_KEY;
      const res = await fetch(url, { headers });
      if (!res.ok) {
        const text = await res.text();
        throw new Error(`Vybsly API ${res.status}: ${text.slice(0, 300)}`);
      }
      return res.json();
    }
Behavior2/5

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

With no annotations, the description carries full burden but only reveals that it produces a synthesized answer with source URLs. It omits behavioral traits such as follow-up handling, source selection logic, rate limits, or authentication requirements, which are critical for safe invocation.

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, focused sentence that conveys the core purpose and output without extraneous information. Every word earns its place, achieving maximum conciseness.

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?

Given the tool's simplicity (2 parameters, no output schema), the description adequately covers the purpose and return format. It could optionally detail citation style or response structure, but the current level suffices for basic understanding.

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?

Both parameters are fully described in the input schema (100% coverage). The description adds minimal semantic value beyond confirming that 'question' is the query and 'max_sources' controls citation count, so 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.

Purpose5/5

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

The description clearly states the tool's function: 'Ask a question, get a sourced AI answer (like Perplexity).' It uses a familiar analogy and specifies the output format, distinguishing it from sibling tools that likely provide raw search results or specific data.

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 is provided on when to use this tool versus alternatives like vybsly_search or vybsly_knowledge. The description does not mention exclusions, prerequisites, or context where this tool is preferable.

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/BlueFusionLab/vybsly-mcp'

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