Skip to main content
Glama
Sign In
agentring

agentring

by mutonby
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

call

Rings the user's phone and lets a voice AI explain the reason, converse, and return the transcript. Blocks until the call ends; unanswered calls trigger a message fallback.

Instructions

Call the user's phone; it rings like a real call. When they answer, a voice AI tells them why you are calling, talks with them, and hangs up when done. Returns the transcript. Blocks until the call ends (or nobody answers, ~30 s of ringing; then the reason and context are sent as a message, fallback_msg_id: read replies with get_replies; not when this server rings only some phones: then nothing is sent and fallback_msg_id is null).

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": {
      "reason": "<reason>"
    },
    "name": "call"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhy you are calling, one sentence; shown on the phone.
urgentNoRing like an alarm, bypassing Do Not Disturb if allowed.
contextNoWhat the voice AI should know, tell or ask the user (it knows nothing else about your work).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so: it discloses that the call BLOCKS until completion, the ~30 s ringing timeout, the automatic fallback message and its id, the null-id case for partial-dial configurations, and that the transcript is returned. These are exactly the traits an agent needs before committing to a blocking side-effecting call.

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?

The core behavior is front-loaded in two short sentences and the return value follows immediately. The final parenthetical is dense and hard to parse on first read, packing timeout, fallback, and null-id edge cases into one nested clause.

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?

There is no output schema, and the description still explains returns (transcript, fallback_msg_id) and the failure path. For a blocking tool with side effects, the timing and fallback details make the definition callable without further guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is already documented, including that 'context' is all the voice AI knows. The description adds no syntax, constraints, or examples beyond the schema; baseline 3 applies.

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 ('Call the user's phone') and immediately describes the interaction model (voice AI explains the reason, converses, hangs up). It is clearly distinguishable from send_message and get_replies by being a synchronous live call rather than an async message.

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?

Usage context is clear: this is for live voice contact, and the no-answer path routes the agent to a message fallback whose replies are read with get_replies. It does not explicitly say when to prefer send_message over a call, so the when-not-to-use side is only implied.

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

Deploy Server

Other Tools