Skip to main content
Glama

Read one answering-line call transcript

get_line_call_transcript
Read-onlyIdempotent

Read the transcript of one call answered by a line you own, with a signed listen link when stored/provider data indicates a recording. Use a line_id from get_answering_line and call_id from get_line_calls; both the line and the call must belong to this owner. Returns status, transcript text, speaker turns, summary and listen_url/listen_expires_at. Calls still being processed and recordings known to be unavailable have no link; the listen endpoint checks actual audio availability. The private link expires after 15 minutes and needs no login: do not publish it. No raw provider recording URL is returned. For a message list use get_line_messages; for call history use get_line_calls. Needs lines:manage; rate limited per account; changes no line settings.

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": {
      "line_id": "<line_id>",
      "call_id": "<call_id>"
    },
    "name": "get_line_call_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
call_idYesThe exact call id from get_line_calls on this line.
line_idYesAn owned line_id from get_answering_line.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations it discloses substantive behavior: the signed listen link is private, expires after 15 minutes, requires no login, must not be published, and no raw provider URL is ever returned. It also explains the edge cases (calls still processing, recordings known unavailable) and that the listen endpoint re-checks actual audio availability, plus the lines:manage scope and per-account rate limiting.

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 purpose and id provenance, then return shape, then edge cases, then alternatives and operational constraints. Every sentence carries information, though the middle section packs return fields, link expiry, and unavailability rules into a dense run that could be split for faster scanning.

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

Completeness5/5

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

There is no output schema, but the description enumerates the return fields (status, transcript text, speaker turns, summary, listen_url/listen_expires_at) so the agent knows what to expect. Combined with auth scope, rate-limit notice, and explicit non-mutation of line settings, nothing material is missing for a two-parameter read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters already carry descriptions, so the baseline is 3. The description adds a constraint the schema does not state: both the line and the call must belong to this owner, which tells the agent that a mismatched pair will fail rather than silently return nothing.

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 first sentence gives a precise verb+resource ('Read the transcript of one call answered by a line you own') and immediately scopes it to a single call, which distinguishes it from the list-style siblings get_line_calls and get_line_messages. An agent can tell exactly what this returns without opening any schema.

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

Usage Guidelines5/5

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

It names the source of each required id ('line_id from get_answering_line and call_id from get_line_calls') and states the ownership precondition. It also routes explicitly to alternatives: 'For a message list use get_line_messages; for call history use get_line_calls.' When-to-use and when-not-to-use are both covered.

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.