Skip to main content
Glama

Dial by Aloha Labs

make_phone_call

Have an AI voice assistant phone a business or person for your human, from your Dial number: book a table, make an appointment, ask a question. It introduces itself as an AI assistant calling on behalf of your human, works toward the goal, and stays within your limits; anything outside them it notes for a callback. Returns a call id at once. Then call get_call_result to wait for the outcome, summary and transcript. US and Canadian numbers only; one call at a time.

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": {
      "api_key": "<api_key>",
      "number_id": "<number_id>",
      "to": "<to>",
      "goal": "<goal>",
      "on_behalf_of": "<on_behalf_of>"
    },
    "name": "make_phone_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesNumber to call, e.g. +13105551234
goalYesWhat the call should achieve, e.g. 'Book a table for 2 this Saturday at 7pm'
voiceNoVoice persona from list_voices, e.g. 'brian' (calm male) or 'sarah' (warm female). 'male'/'female' also work.
api_keyYesYour Dial API key (from sign_up)
detailsNoFacts the assistant may share: reservation name, party size, a callback number, preferences
number_idYesid of your number (from get_phone_number); the call comes from it
may_agree_toNoLimits, e.g. 'any time 6:30-8:30pm; no deposit'. Without this it agrees only to exactly the goal.
on_behalf_ofYesYour human's name, e.g. 'Berk Cagatay'
assistant_nameNoYour own first name; the call opens 'Hi, this is <name>, an AI assistant calling for <human>'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the AI self-introduction script, that the assistant stays within the caller's stated limits and flags anything outside them for a callback, that the call is asynchronous ("returns a call id at once"), plus geographic and one-call-at-a-time constraints. These are exactly the operational facts an agent cannot infer from the schema.

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 outcome and audience, then constraints, then the follow-up call, in about three dense sentences with no filler. Every clause contributes an operational fact.

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?

No output schema exists, yet the description covers the return value (a call id immediately) and points to get_call_result for outcome, summary and transcript. Combined with the documented async model and eligibility limits, an agent has everything needed to invoke and follow up 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; the description still adds value by tying number_id to the call's origin, framing on_behalf_of as the human the call is for, and explaining the consequence of may_agree_to (out-of-limit requests are noted for callback) rather than just its format.

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 concrete verb and resource (AI voice assistant places a phone call) plus the use cases (book a table, make an appointment, ask a question) and the scoping detail that the call is placed from the user's Dial number. It is clearly distinguished from get_call_result, which it names as the separate outcome-fetching step rather than conflating the two.

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?

Gives explicit sequencing ("Then call get_call_result to wait for the outcome") and hard constraints ("US and Canadian numbers only; one call at a time"). It implies prerequisites via the parameter context, but never states when not to use this tool, e.g. versus read_text_messages for messaging.

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.