Skip to main content
Glama

get_call_transcript

Read-onlyIdempotent

Retrieve full conversation text and summaries from completed calls using a call ID to review phone discussions and extract important details.

Instructions

Get the transcript for a completed call. Returns the full conversation text and summary.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
call_idYesThe call ID

Implementation Reference

  • The handler function for get_call_transcript tool. It's an async arrow function that receives params with call_id, and uses callTool helper to make a GET request to /calls/{call_id}/transcript endpoint.
    server.registerTool(
      "get_call_transcript",
      {
        description: "Get the transcript for a completed call. Returns the full conversation text and summary.",
        inputSchema: {
          call_id: z.string().describe("The call ID"),
        },
        annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false },
      },
      async (params) => callTool(() => client.get(`/calls/${params.call_id}/transcript`))
    );
  • Input schema definition for get_call_transcript using Zod validation. Defines call_id as a required string parameter with description. Also includes tool annotations (readOnlyHint: true, destructiveHint: false, idempotentHint: true).
    server.registerTool(
      "get_call_transcript",
      {
        description: "Get the transcript for a completed call. Returns the full conversation text and summary.",
        inputSchema: {
          call_id: z.string().describe("The call ID"),
        },
        annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false },
      },
      async (params) => callTool(() => client.get(`/calls/${params.call_id}/transcript`))
    );
  • Registration of the get_call_transcript tool with the MCP server using server.registerTool(). Includes tool name, description, input schema, annotations, and handler function.
    server.registerTool(
      "get_call_transcript",
      {
        description: "Get the transcript for a completed call. Returns the full conversation text and summary.",
        inputSchema: {
          call_id: z.string().describe("The call ID"),
        },
        annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false },
      },
      async (params) => callTool(() => client.get(`/calls/${params.call_id}/transcript`))
    );
  • The callTool helper function that wraps API calls with error handling. It executes the provided async function, formats successful results using toolResult(), and catches errors to return formatted error messages using toolError().
    async function callTool<T>(fn: () => Promise<T>) {
      try {
        return toolResult(await fn());
      } catch (err) {
        const apiErr = err as ApiError;
        return toolError(`API error (${apiErr.status}): ${apiErr.message}`);
      }
    }
  • The BubblyPhoneClient.get() method used by the handler to make HTTP GET requests. Constructs URL with query parameters and calls the private request method with authentication headers.
    async get<T = unknown>(path: string, params?: Record<string, string>): Promise<T> {
      const url = new URL(`${this.baseUrl}${path}`);
      if (params) {
        for (const [key, value] of Object.entries(params)) {
          if (value !== undefined && value !== "") {
            url.searchParams.set(key, value);
          }
        }
      }
      return this.request<T>(url.toString(), { method: "GET" });
    }
Behavior4/5

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

While annotations declare readOnly/idempotent status, the description adds valuable behavioral context: it specifies the return value ('full conversation text and summary') and the completion status requirement ('completed call') which annotations don't cover.

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 with zero waste: first establishes purpose and constraint (completed call), second discloses return values. Perfectly front-loaded and appropriately sized.

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?

For a simple single-parameter retrieval tool, the description adequately compensates for the missing output schema by describing return values ('text and summary'). Annotations provide safety context. Minor gap: doesn't indicate where to obtain the call_id.

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?

With 100% schema description coverage for the single 'call_id' parameter, the schema carries the semantic burden. The description doesn't add parameter details (e.g., format, where to obtain it), but none are needed given the comprehensive schema.

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 uses a specific verb ('Get') with a specific resource ('transcript') and distinguishes from sibling tools like 'get_call' (metadata) by specifying 'transcript' and 'full conversation text'.

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 phrase 'for a completed call' implies a usage constraint (don't use on active calls), but there are no explicit when-not guidelines or named alternatives like 'use get_call for metadata instead'.

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/JobXDubai/mcp-server'

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