Skip to main content
Glama

search_ideas

Read-only

Find ideas by searching titles and summaries, with filters for status, source, and result limits to support product feedback management.

Instructions

Search ideas by text query. Searches title and summary fields.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query text
statusNoFilter by status
sourceNoFilter by source
limitNoNumber of results to return

Implementation Reference

  • Definition and registration of the 'search_ideas' tool in proxyTools.ts. The tool is proxied to the main application's MCP handler via handleProxyTool.
      name: 'search_ideas',
      description: 'Search ideas by text query. Searches title and summary fields.',
      inputSchema: {
        type: 'object' as const,
        properties: {
          query: { type: 'string', description: 'Search query text' },
          status: {
            type: 'string',
            enum: ['new', 'accepted', 'rejected', 'snoozed', 'expired'],
            description: 'Filter by status',
          },
          source: { type: 'string', description: 'Filter by source' },
          limit: { type: 'number', description: 'Number of results to return', default: 20 },
        },
        required: ['query'],
      },
      annotations: { readOnlyHint: true, destructiveHint: false, openWorldHint: true },
      _meta: { 'openai/visibility': 'public' },
    },
  • The handleProxyTool function acts as the handler for 'search_ideas' (and other proxied tools), forwarding the call to the main IdeaLift app via idealiftClient.mcpProxy.
    export async function handleProxyTool(
      toolName: string,
      args: Record<string, unknown>,
      chatgptSubjectId: string
    ): Promise<{ content: Array<{ type: string; text: string }>; isError: boolean }> {
      try {
        const response = await idealiftClient.mcpProxy(
          chatgptSubjectId,
          'tools/call',
          { name: toolName, arguments: args }
        );
    
        if (response.error) {
          return {
            content: [{ type: 'text', text: `Error: ${response.error.message}` }],
            isError: true,
          };
        }
    
        // The result from handleJsonRpcRequest for tools/call is { content: [...], isError?: boolean }
        const result = response.result as { content?: Array<{ type: string; text: string }>; isError?: boolean } | undefined;
    
        if (result?.content) {
          return {
            content: result.content,
            isError: result.isError || false,
          };
        }
    
        // Fallback: wrap the result as text
        return {
          content: [{ type: 'text', text: JSON.stringify(response.result, null, 2) }],
          isError: false,
        };
      } catch (error) {
        console.error(`[ProxyTool] Error calling ${toolName}:`, error);
        return {
          content: [{ type: 'text', text: `Proxy error: ${(error as Error).message}` }],
          isError: true,
        };
      }
    }
Behavior3/5

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

Annotations declare readOnlyHint=true and destructiveHint=false, establishing safety. Description adds that search targets 'title and summary fields' (internal scope not obvious from name). However, fails to clarify openWorldHint=true implications (varying results/external data) or describe output format/pagination behavior.

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?

Extremely concise two-sentence structure with zero redundancy. First sentence states purpose, second specifies search scope. Appropriate length for the tool's complexity.

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

Completeness3/5

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

Adequate for a simple search tool with excellent schema coverage and safety annotations, but lacks output value description (no output schema exists) and misses opportunity to differentiate from similar sibling tools (query_ideas vs search_ideas).

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?

Schema coverage is 100% with complete descriptions for all 4 parameters. Description mentions 'text query' reinforcing the query parameter's purpose and specifies searched fields, but does not add semantic details beyond what the schema already provides for status, source, or limit.

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?

Clear verb (search) and resource (ideas). Specifies scope by mentioning 'title and summary fields' as search targets. However, does not explicitly distinguish from siblings like 'query_ideas' or 'list_ideas' which likely perform similar operations.

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 provided on when to use this tool versus alternatives like list_ideas, query_ideas, or get_idea. No mention of required authentication from check_auth or prerequisites.

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