Skip to main content
Glama

A call's transcript

call_transcript
Read-onlyIdempotent

The transcript and summary of one call, as stored by cpass: who said what, turn by turn, plus the agent's call summary and any transfer summary. Takes a call's unique id. Many calls have no stored transcript yet; that is reported plainly, not as an error. Read only.

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": {
      "callId": "<callId>"
    },
    "name": "call_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
callIdYesThe call's unique id (call_id), or its numeric row_id
maxTurnsNoMost turns to return, default 300

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / callId / description
      Previous value: -"The call_id (unique id) from call_list, the callId from outbound_call, or a numeric row_id"New value: +"The call's unique id (call_id), or its numeric row_id"
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world behavior, so the bar is low; the description still adds a genuinely useful behavioral fact that a missing transcript is reported plainly rather than as an error. The closing 'Read only' merely restates the annotation, but the empty-result disclosure is real added value.

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?

Front-loaded with the returned content, then the input, then the empty-state caveat. Four short sentences with almost no waste; only the trailing 'Read only' duplicates the annotations and could be dropped.

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 single-record read with no output schema, the description does the heavy lifting by enumerating return content and the missing-transcript case. The remaining gap is that maxTurns implies truncation but the description never says what happens when a call exceeds the turn limit.

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%, so callId (call_id or numeric row_id) and maxTurns (default 300, max 1000) are already documented in the schema. The description only echoes the id requirement and says nothing about maxTurns or what truncation means, so it adds little beyond structured data.

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 retrieval: the transcript and summary of one call, broken out as who-said-what turn by turn plus agent and transfer summaries. An agent knows exactly what content comes back, though the description does not explicitly distinguish this from the sibling call_summary tool despite covering overlapping summary content.

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 implied by 'Takes a call's unique id' and the note that many calls have no stored transcript, but there is no explicit when-to-use framing or named alternative for getting just a summary or just an outcome. The agent must infer the routing itself.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.