Skip to main content
Glama
jgottlieb84

agentline-mcp

by jgottlieb84
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

make_call

Initiate an outbound AI voice call. The AI agent follows your system prompt and speaks a first message when the recipient answers. Returns a call ID immediately; poll to get status, transcript, and summary.

Instructions

Place an outbound AI voice call. An AI agent answers when the recipient picks up and follows prompt as its system instructions; first_message is what it says on connect.

Returns immediately with the id (call_id) — the call runs in the background. Poll get_call(call_id) to see status, transcript, and summary once it completes.

voice is a Deepgram TTS voice (aura-asteria-en, aura-orion-en, …).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
from_numberYes
to_numberYes
promptYes
first_messageNo
voiceNoaura-asteria-en
llm_modelNoclaude-sonnet-4-20250514
max_duration_secondsNo

Implementation Reference

  • agentline_mcp/server.py:201-234 (handler)
    The 'make_call' tool handler function. Decorated with @mcp.tool(), it takes parameters (from_number, to_number, prompt, first_message, voice, llm_model, max_duration_seconds) and delegates to the Agentline SDK's make_call() method, returning the result as a dict via asdict(). Catches AgentlineError and returns error info.
    @mcp.tool()
def make_call(
    from_number: str,
    to_number: str,
    prompt: str,
    first_message: str | None = None,
    voice: str = "aura-asteria-en",
    llm_model: str = "claude-sonnet-4-20250514",
    max_duration_seconds: int = 300,
) -> dict:
    """Place an outbound AI voice call. An AI agent answers when the recipient
    picks up and follows `prompt` as its system instructions; `first_message` is
    what it says on connect.

    Returns immediately with the `id` (call_id) — the call runs in the
    background. Poll `get_call(call_id)` to see status, transcript, and summary
    once it completes.

    `voice` is a Deepgram TTS voice (aura-asteria-en, aura-orion-en, …).
    """
    try:
        result = _client_or_init().make_call(
            from_=from_number,
            to=to_number,
            prompt=prompt,
            voice=voice,
            first_message=first_message,
            llm_model=llm_model,
            max_duration_seconds=max_duration_seconds,
            wait=False,
        )
        return asdict(result)
    except AgentlineError as e:
        return {"error": str(e), "status_code": e.status_code}
  • agentline_mcp/server.py:201-201 (registration)
    The tool is registered as an MCP tool via the @mcp.tool() decorator on line 201, where 'mcp' is a FastMCP instance created on line 47 as 'mcp = FastMCP("agentline")'.
    @mcp.tool()
  • agentline_mcp/server.py:51-55 (helper)
    Helper function _client_or_init() that lazily initializes and returns the Agentline client singleton used by make_call.
    def _client_or_init() -> Agentline:
    global _client
    if _client is None:
        _client = _build_client()
    return _client

Tool Definition Quality

A4.3/5.0
Behavior4/5

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

Despite no annotations, the description discloses key behavioral traits: immediate return with id, background execution, AI agent follows prompt and first_message. Sufficient for an async voice call tool.

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?

Three short paragraphs, each sentence adds value. Front-loaded with purpose. No wasted words.

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

Completeness3/5

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

Covers the main flow and async pattern but lacks details on error handling, max_duration_seconds behavior, and return value structure beyond id. Adequate for typical use but has gaps.

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?

Adds meaning beyond schema for prompt, first_message, and voice (explains purpose and examples). Schema coverage is 0%, so description compensates well but misses llm_model and max_duration_seconds.

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 description clearly states the tool 'places an outbound AI voice call' with specific details about the AI agent and background execution. It distinguishes itself from siblings like get_call and hangup_call by explaining the async flow.

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

Usage Guidelines4/5

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

Provides clear context for usage: outbound AI call, returns immediately, poll get_call for results. No explicit exclusions or alternatives, but the usage pattern is well implied.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jgottlieb84/agentline-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server