Dialpad MCP server

dialpad_get_call_transcript

Read-onlyIdempotent

Retrieve a Dialpad AI call transcript by call ID, returning up to a set number of lines with timestamps, speaker names, and text. Access is admin-gated for privacy.

Instructions

Get the Dialpad AI transcript of a call: each line with time, speaker name, type (transcript or moment) and text. Returns up to max_lines lines (default 400). Contains personal information - admin-gated.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "call_id": "<call_id>"
    },
    "name": "dialpad_get_call_transcript"
  }
}

Input Schema

Name	Required	Description	Default
`call_id`	Yes	Call ID (numeric).
`max_lines`	No	Most lines to return (default 400).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), and the description adds meaningful context on top: it flags that the payload contains personal information and is 'admin-gated', which signals an authorization prerequisite. The default of 400 lines and the cap behavior are also disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the resource and return shape, then the limit, then the access caveat. Dense and mostly waste-free, though the trailing 'Contains personal information - admin-gated' fragment could be phrased as a clearer precondition.

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?

With no output schema, the description usefully describes the per-line structure and the line cap, and it discloses the admin gate. It does not say whether truncation indicates more content available or how to page past max_lines, which is a real gap for a 2000-line-capable tool.

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 description coverage is 100%, so the schema already documents both call_id and max_lines (including default 400 and the 1-2000 range). The description restates the max_lines default without adding new semantics, which is the baseline case.

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?

States a specific verb and resource ('Get the Dialpad AI transcript of a call') and enumerates the returned fields (time, speaker name, type, text), which clearly separates it from dialpad_get_call metadata. It stops short of naming a sibling alternative explicitly, so it is clear but not fully differentiated by name.

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?

Usage is only implied: an agent can infer to call this when it needs the transcript rather than the call record. There is no explicit when-to-use/when-not guidance, no mention of what to use instead for call metadata, and no note about what happens if a call has no AI transcript.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.