Skip to main content
Glama

get_live_transcript

Read-onlyIdempotent

Fetch live transcript segments from an ongoing call recording, using a cursor and short wait for new speech, to monitor the conversation and prepare real-time follow-up questions.

Instructions

Live transcript of the recording in progress (started with live=true): what was said since the cursor since, about a second after each sentence ends. Waits up to wait_seconds for new speech. Rough text: the final transcript after the call is more accurate.

To follow a call and help the user in real time, call it in a loop within the same turn, passing the returned cursor as since. After each batch, tell the user in a few lines (they are on the call, keep it short): which of their planned questions got answered, where the other side stayed vague, evasive or unconvincing, and one or two precise follow-up questions to ask now. Say nothing when a batch brings nothing useful. Stop when the recording is over.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_live_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNo
wait_secondsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.3.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, but the description adds behavior the annotations cannot: ~1 second latency after each sentence, blocking up to wait_seconds for new speech, cursor-based incremental delivery, and the accuracy caveat ('Rough text'). That is exactly the context needed to loop safely without misinterpreting partial output.

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?

Purpose and behavior are front-loaded in the first sentence, and the second paragraph is purposeful loop guidance rather than filler. It is still long, and the detailed coaching on what to say to the user (planned questions, evasiveness, follow-ups) is workflow advice that could be condensed without loss.

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?

With annotations covering safety, an output schema covering return shape, and just two optional parameters, the description supplies everything else an agent needs: latency expectations, cursor chaining, loop and stop conditions, and the quality tradeoff. Nothing necessary to call it correctly is missing.

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 description coverage is 0%, so the description must carry the parameters, and it does define both: `since` as the cursor returned by the prior call (the batch boundary) and `wait_seconds` as a bounded block for new speech. It stops short of saying what `since=0` means (start from the beginning) or the units/validity of the cursor, leaving a small gap.

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?

States a specific verb and resource ('live transcript of the recording in progress') and pins the precondition to a sibling ('started with live=true'). It also implicitly separates itself from the post-call transcript by noting 'the final transcript after the call is more accurate', so an agent can tell it apart from get_transcript.

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?

Gives an explicit when-to-use scenario ('To follow a call and help the user in real time'), the invocation pattern ('call it in a loop within the same turn, passing the returned cursor as since'), and a stop condition ('Stop when the recording is over'). It also contrasts with the more accurate final transcript, which routes the agent away from this tool for post-hoc work.

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