Skip to main content
Glama
huiseo

Outline Wiki MCP Server

by huiseo

ask_wiki

Get answers to questions by retrieving relevant information from wiki content using RAG technology.

Instructions

Ask a question and get an answer based on wiki content using RAG.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYes

Implementation Reference

  • The core handler function for the 'ask_wiki' tool. It checks if the brain (AI/vector store) is enabled, then queries it with the user's question using RAG to retrieve an answer and relevant sources.
    async ask_wiki(args: { question: string }) {
      if (!brain.isEnabled()) {
        return { error: ERROR_MESSAGES.SMART_FEATURES_DISABLED };
      }
    
      const { answer, sources } = await brain.ask(args.question);
    
      return {
        answer,
        sources: sources.map((s) => ({
          title: s.title,
          url: s.url,
        })),
      };
    },
  • Zod schema defining the input for the 'ask_wiki' tool: requires a 'question' string.
    export const askWikiSchema = z.object({
      question: z.string().min(1, 'Question is required'),
    });
  • Registers the smart handlers (including 'ask_wiki') by spreading createSmartHandlers into the full set of tool handlers.
    export function createAllHandlers(ctx: AppContext): ToolHandlers {
      return {
        ...createSearchHandlers(ctx),
        ...createDocumentHandlers(ctx),
        ...createCollectionHandlers(ctx),
        ...createCommentHandlers(ctx),
        ...createBatchHandlers(ctx),
        ...createSmartHandlers(ctx),
      } as ToolHandlers;
    }
  • Registers the 'ask_wiki' tool definition for MCP, including name, description, and schema reference.
    createTool(
      'ask_wiki',
      'Ask a question and get an answer based on wiki content using RAG.',
      'ask_wiki'
    ),
  • Maps the 'ask_wiki' tool name to its Zod schema in the central toolSchemas object.
    ask_wiki: askWikiSchema,
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. It mentions using RAG (Retrieval-Augmented Generation), which implies AI-generated answers based on retrieved content, but doesn't detail aspects like response format, potential inaccuracies, rate limits, authentication needs, or whether it modifies data. For a tool with no annotations, this leaves significant gaps in understanding its operation and constraints.

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, efficient sentence: 'Ask a question and get an answer based on wiki content using RAG.' It's front-loaded with the core action and method, with no wasted words or redundancy, making it easy to parse quickly.

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 tool's complexity (involving RAG and wiki content), lack of annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't explain what the output looks like (e.g., text answer, citations), error conditions, or how it interacts with the wiki system. For a query tool with AI components, more context on reliability and scope is needed.

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 1 parameter (question) with 0% description coverage, meaning the schema provides no semantic details. The description adds value by implying the parameter is a question to be answered using wiki content and RAG, but it doesn't specify format, length limits, or examples. Since schema coverage is low, the description partially compensates but not fully, aligning with the baseline for minimal param info.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Ask a question and get an answer based on wiki content using RAG.' It specifies the verb ('ask'), resource ('wiki content'), and method ('RAG'), making it distinct from siblings like search_documents or get_document. However, it doesn't explicitly differentiate from find_related or summarize_document, which might have overlapping query functionality.

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. With siblings like search_documents, get_document, and find_related that might handle queries or content retrieval, there's no indication of when ask_wiki is preferred, such as for open-ended questions versus specific document lookups, or any prerequisites like needing existing wiki content.

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/huiseo/outline-smart-mcp'

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