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

Smitline: AI Phone Calls & Meetings

Guide a call in progress

send_call_instruction

Send new guidance or a changed plan to an in-progress call or meeting so the voice agent acts on it at the next pause, optionally keeping it as a silent background note.

Instructions

Pass new guidance to the voice during a phone call or meeting that is still in progress, for example an answer the user just gave or a change of plan. The voice gets it as a note from the user's agent and acts on it right away, telling the people on the call anything in it meant for them at the next pause; with silent: true it keeps it as a background note and uses it when relevant. Not for answering a request from the call: reply_to_call_request does that and the voice says it, so sending it here too makes the voice say it twice. Errors with conflict once the call has ended. To end the call use end_call; to take it over use transfer_call_to_me. Then keep following the call with wait_for_call.

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>",
      "text": "<text>"
    },
    "name": "send_call_instruction"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
callIdYesCall id returned by start_call, such as call-0123456789abcdef
silentNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations by explaining the delivery mechanics: the voice receives it as a note and relays relevant content at the next pause, while silent:true demotes it to a background note. It also discloses the conflict error after the call ends and the duplicate-speech side effect. It stops short of stating whether the call is in any way modified or what confirmation is returned, which keeps it off a 5.

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

Conciseness5/5

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

Front-loaded with the action and scope, then the delivery behavior, then the exclusions, then the error condition and sibling routing. Every sentence carries distinct information; nothing is repeated from the schema or annotations.

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?

Complete enough to call correctly: required params are covered, silent is explained, failure mode (conflict after call end) is named, and related tools are routed. The only gap is that no output schema exists and the description never says what is returned on success, so an agent cannot anticipate the response shape.

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?

At 33% schema coverage the description must compensate, and it does for the two undocumented params: silent:true is defined behaviorally ('keeps it as a background note and uses it when relevant') and text is characterized by example ('an answer the user just gave or a change of plan'). callId is already described in the schema. Only the 2000-char bound and silent's default are left unmentioned.

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 ('Pass new guidance to the voice') scoped to a call or meeting still in progress, and immediately contrasts with the sibling that handles the confusable case (reply_to_call_request). An agent can distinguish this from end_call, transfer_call_to_me, and reply_to_call_request 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?

Gives explicit when-to-use ('an answer the user just gave or a change of plan'), explicit when-not-to-use and why ('Not for answering a request from the call... sending it here too makes the voice say it twice'), plus named alternatives for the two adjacent intents (end_call, transfer_call_to_me) and a follow-up step (wait_for_call).

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