Skip to main content
Glama

Summarize Text

summarize

Summarize meeting transcripts or notes using AI. Provide optional guidance like action items or executive summary.

Instructions

Summarize transcript text via GhostMinutes hosted AI (/api/ai/chat). Paste transcript content or downstream output from get_transcript.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesTranscript or notes text to summarize.
focusNoOptional guidance (e.g. "action items only", "executive summary").

Implementation Reference

  • The main handler for the 'summarize' tool. It calls `server.registerTool('summarize', ...)` with a callback that requires auth, builds a system prompt (optionally including a focus directive), sends the user's text to `client.aiChat()`, and returns both plain text and structured content.
    export function register(server: McpServer, client: GhostMinutesClient): void {
      server.registerTool(
        'summarize',
        {
          title: 'Summarize Text',
          description:
            'Summarize transcript text via GhostMinutes hosted AI (/api/ai/chat). Paste transcript content or downstream output from get_transcript.',
          inputSchema: z.object({
            text: z
              .string()
              .min(1)
              .describe('Transcript or notes text to summarize.'),
            focus: z
              .string()
              .optional()
              .describe(
                'Optional guidance (e.g. "action items only", "executive summary").',
              ),
          }),
          annotations: { readOnlyHint: false, openWorldHint: true },
        },
        async ({ text, focus }) => {
          requireAuth(client);
          const systemPrompt =
            focus?.trim()?.length ?
              `You summarize transcripts accurately and concisely. Focus: ${focus}`
            : 'You summarize transcripts accurately and concisely.';
          const messages = [{ role: 'user', content: text }];
          const body = await client.aiChat(messages, systemPrompt);
          return {
            content: [{ type: 'text', text: JSON.stringify(body, null, 2) }],
            structuredContent: jsonStructured(body),
          };
        },
      );
    }
  • Input schema for the summarize tool. Accepts a required 'text' string (transcript/notes) and an optional 'focus' string for guidance (e.g., 'action items only').
    inputSchema: z.object({
      text: z
        .string()
        .min(1)
        .describe('Transcript or notes text to summarize.'),
      focus: z
        .string()
        .optional()
        .describe(
          'Optional guidance (e.g. "action items only", "executive summary").',
        ),
    }),
  • src/server.ts:9-9 (registration)
    Import of the register function from src/tools/summarize.ts into the server.
    import { register as registerSummarize } from './tools/summarize.js';
  • src/server.ts:20-20 (registration)
    'summarize' is listed in the EXPECTED_TOOL_NAMES array of the server.
    'summarize',
  • src/server.ts:38-38 (registration)
    Registration call: registerSummarize(server, client) wires the tool into the MCP server.
    registerSummarize(server, client);
Behavior3/5

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

Annotations indicate read-only is false and open-world is true. Description adds that it uses a specific AI endpoint (/api/ai/chat), but does not detail potential costs, rate limits, or text length 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?

Two sentences, no wasted words. Purpose and source guidance are front-loaded and clear.

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?

Tool is simple with two parameters. Description mentions the AI endpoint, which implies cost or side effects. Lacks return format details, but schema is complete and tool is straightforward.

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 covers both parameters with descriptions. The description adds minimal value beyond the schema, such as example values for the focus parameter.

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 summarizes transcript text via GhostMinutes hosted AI, distinguishing it from sibling tools like get_transcript which retrieves raw text.

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

Usage Guidelines4/5

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

Explicitly advises to paste transcript content or use output from get_transcript, providing clear context. Does not mention when to avoid using it, but purpose is sufficiently clear.

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/Rocketech-Software-Development/ghostminutes-mcp'

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