Skip to main content
Glama

search

Search your Vaiz workspace for tasks, projects, users, comments, boards, or documents using keywords.

Instructions

Search for entities in YOUR workspace (tasks, projects, users, comments, boards, USER documents). NOT system documentation!

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
entityTypeNotask
queryYes
limitNo

Implementation Reference

  • Hardcoded schema definition for the 'search' tool as part of the VAIZ_TOOLS array. Defines the tool name as 'search', its description, and input schema with entityType (enum: task/project/user/comment/board/document, default: task), query (required, minLength: 1), and limit (1-50, default: 10).
    export const VAIZ_TOOLS: Tool[] = [
      {
        name: 'search',
        description:
          'Search for entities in YOUR workspace (tasks, projects, users, comments, boards, USER documents). NOT system documentation!',
        inputSchema: {
          type: 'object',
          properties: {
            entityType: {
              type: 'string',
              enum: ['task', 'project', 'user', 'comment', 'board', 'document'],
              default: 'task',
            },
            query: { type: 'string', minLength: 1 },
            limit: { type: 'number', minimum: 1, maximum: 50, default: 10 },
          },
          required: ['query'],
          additionalProperties: false,
        },
      },
  • Handler registration in proxy-server.ts. The CallToolRequestSchema handler at line 481 is the generic handler that processes ALL tool call requests, including 'search'. It proxies the call to the remote Vaiz HTTP MCP API via proxyToRemote('tools/call', request.params), meaning the actual search execution logic is on the remote server. The ListToolsRequestSchema handler at line 463 merges the hardcoded VAIZ_TOOLS (including 'search') with remote tool definitions.
    private registerHandlers(): void {
      const lowLevel = this.mcpServer.server;
    
      lowLevel.setRequestHandler(ListToolsRequestSchema, async () => {
        this.log('← tools/list');
        try {
          const result = (await this.proxyToRemote('tools/list')) as {
            tools?: Tool[];
          };
          const remoteTools = result?.tools ?? [];
          return { tools: mergeByName(VAIZ_TOOLS, remoteTools) };
        } catch {
          const cached = this.responseCache.get('tools/list') as {
            tools?: Tool[];
          } | undefined;
          return {
            tools: mergeByName(VAIZ_TOOLS, cached?.tools ?? []),
          };
        }
      });
    
      lowLevel.setRequestHandler(CallToolRequestSchema, async (request) => {
        this.log(`← tools/call ${request.params.name}`);
        const result = await this.proxyToRemote('tools/call', request.params);
        return result as { content: Array<{ type: string; text: string }> };
      });
  • src/tools.ts:8-8 (registration)
    Export of the VAIZ_TOOLS array which includes the 'search' tool definition. This array is imported by proxy-server.ts (line 15) and used in tool registration.
    export const VAIZ_TOOLS: Tool[] = [
Behavior2/5

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

No annotations are provided, so the description carries full burden. It adds scope (your workspace) and exclusion (not system docs) but fails to disclose behavioral traits like pagination, rate limits, authentication needs, or whether partial matches are supported. This is a significant gap for a search tool.

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 that immediately states the tool's purpose. It is front-loaded with the action verb 'Search' and efficiently communicates key scope information without superfluous words.

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 has three parameters (one required), no output schema, and no annotations, the description is too brief. It does not cover search behavior (e.g., fuzzy vs exact), output format, or error handling, leaving the agent with insufficient context to use the tool reliably.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, meaning input schema lacks descriptions. The description does not elaborate on parameters (e.g., entityType values, query format, limit behavior), so it adds minimal meaning beyond the schema structure.

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?

Description clearly states it searches for specific entity types (tasks, projects, users, comments, boards, documents) in the user's workspace, explicitly excluding system documentation. This provides a specific verb and resource scope, distinguishing it from potential misinterpretations.

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

Usage Guidelines3/5

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

The description implies when to use (to find workspace entities) and explicitly excludes system documentation, but it does not provide context on when not to use or mention any alternatives among sibling tools (none are search tools). No prerequisites or limitations are stated.

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/vaizcom/vaiz-mcp'

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