Skip to main content
Glama
Smitline: AI Phone Calls & Meetings

Smitline: AI Phone Calls & Meetings

Follow a call live

wait_for_call
Read-only

Keep following a live call after it starts: receive new transcript lines and incoming requests as they arrive, answer them, and get the final outcome when the call ends.

Instructions

Follow a call live until it ends. Call it right after start_call and keep calling it in the same turn until status is completed, failed, or canceled: once your turn ends, nothing from the call reaches you, and people waiting on you get no answer. Pass since: "" the first time (the default), then live.cursor from the last answer. It returns at once when someone on the call asks you for something (brief canDo), when the status changes, and at the end; otherwise once new talk has gathered, so each answer carries an exchange or two, with live.transcript holding the new lines (speaker agent is Smitline; other or meeting is the people on the call). live.requests holds requests: id, kind question or task, text, askedBy, and the last lines said (source: "speech" when the text is what the person said, passed on because the voice said it would). Answer each with reply_to_call_request, then wait again. Step in with send_call_instruction only when you know something the call needs, or end_call if it goes wrong. A finished call has its result: outcome, summary, details such as confirmation numbers, decisions, action items, open questions, openRequests, and the transcript; tell the user the outcome in plain words. next, the first field, says what to do now. For a long meeting pass only: "requests" to wake only for requests and the end, without the transcript.

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": "wait_for_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
onlyNoWake only for requests from the call and the end, and leave out the transcript.
sinceNo"" the first time (the default: from the start), then live.cursor from the last answer, so nothing comes twice.
callIdYesCall id returned by start_call, such as call-0123456789abcdef
othersNoAlso watch your other calls in progress (default true): a new request on any of them wakes this wait, and live.otherRequests lists every request on them you have not answered yet (callId, id, text). Answer those with reply_to_call_request on their own callId, so a call you are busy with never hides another.
timeoutSecondsNoHow long to wait in this request. Default 50.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.3.12
    • changedInput schema / properties / only / description
      Previous value: -"Wake only for requests from the call, and leave out the transcript. Implies following live."New value: +"Wake only for requests from the call and the end, and leave out the transcript."
    • changedInput schema / properties / others / description
      Previous value: -"While following live, also watch your other calls in progress (default true): a new request on any of them wakes this wait, and live.otherRequests lists every request on them you have not answered yet (callId, id, text). Answer those with reply_to_call_request on their own callId, so a call you are busy with never hides another."New value: +"Also watch your other calls in progress (default true): a new request on any of them wakes this wait, and live.otherRequests lists every request on them you have not answered yet (callId, id, text). Answer those with reply_to_call_request on their own callId, so a call you are busy with never hides another."
    • changedInput schema / properties / since / description
      Previous value: -"Follow the call live: \"\" the first time, then live.cursor from the last answer."New value: +"\"\" the first time (the default: from the start), then live.cursor from the last answer, so nothing comes twice."
  2. Changed1 schema field changedv0.3.5
    • addedInput schema / properties / others
      Added value: +{
      +  "description": "While following live, also watch your other calls in progress (default true): a new request on any of them wakes this wait, and live.otherRequests lists every request on them you have not answered yet (callId, id, text). Answer those with reply_to_call_request on their own callId, so a call you are busy with never hides another.",
      +  "type": "boolean"
      +}
  3. Changed2 schema fields changedv0.3.0
    • addedInput schema / properties / only
      Added value: +{
      +  "description": "Wake only for requests from the call, and leave out the transcript. Implies following live.",
      +  "enum": [
      +    "requests"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / since
      Added value: +{
      +  "description": "Follow the call live: \"\" the first time, then live.cursor from the last answer.",
      +  "pattern": "^[0-9]{0,12}$",
      +  "type": "string"
      +}
  4. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the real burden and does: it explains the long-poll wake conditions (request, status change, end, or accumulated talk), the consequence of ending the turn ('nothing from the call reaches you'), the shape of live.transcript and live.requests, and what a finished call contains.

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 the critical 'keep calling in the same turn' constraint are front-loaded, and nearly every clause carries operational information. It is dense and semicolon-heavy, and a few parentheticals (e.g. the 'source: speech' aside) could be tightened, but nothing is filler.

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 no output schema, the description must document returns and does: live.transcript, live.requests fields, next, and the finished-call result (outcome, summary, details, openRequests, transcript). An agent has everything needed to drive the poll loop correctly.

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%, so the baseline is 3, but the description adds meaning beyond it: the since cursor progression ('"" the first time, then live.cursor from the last answer') and the purpose of only:"requests" for long meetings. timeoutSeconds and others are left to the 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?

States a specific verb and resource — 'Follow a call live until it ends' — and immediately contrasts with named siblings (start_call, reply_to_call_request, send_call_instruction, end_call), so an agent can place it in the call workflow without opening another 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?

Gives explicit when-to-use ('right after start_call and keep calling it in the same turn until status is completed, failed, or canceled'), when-not ('Step in with send_call_instruction only when you know something the call needs'), an error path ('end_call if it goes wrong'), and a variant ('For a long meeting pass only: "requests"'). The cost of not calling is spelled out.

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