Skip to main content
Glama
AgentPhone-AI

AgentPhone MCP Server

Official

create_agent

Create an agent to own phone numbers and handle calls or SMS, choosing hosted AI voice or webhook transcript forwarding.

Instructions

Create a new agent. An agent owns phone numbers and handles calls/SMS.

A newly created agent has no phone number until one is attached. Set voice_mode to 'hosted' with a system_prompt for autonomous AI voice calls, or 'webhook' (default) to forward call transcripts to your webhook URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName for the agent (e.g. 'Customer Support', 'Sales Bot')
voiceNoVoice ID for the agent. Defaults to 'Skylar - Friendly Guide'.
languageNoBCP-47 locale for speech recognition and synthesis, e.g. 'en-US', 'es-ES', 'ja-JP'.
stt_modeNoSpeech-to-text mode: 'fast' (default) lowest latency, 'accurate' for exact names/numbers (~200ms slower).
model_tierNoModel quality/speed tier for hosted-mode agents. 'turbo' = fastest/cheapest, 'balanced' (default) = general use, 'max' = highest quality.
voice_modeNo'webhook' (default) forwards transcripts to your webhook. 'hosted' uses built-in AI with system_prompt.
descriptionNoDescription of what this agent does
voice_speedNoSpeech speed multiplier. 1.0 = normal, 0.5 = half speed, 2.0 = double.
ambient_soundNoOptional background ambience for call audio. Not a substitute for the AI self-identification, which is always disclosed.
begin_messageNoWhat the AI says when a call connects. Only used in 'hosted' mode.
system_promptNoRequired when voice_mode is 'hosted'. The AI's personality and instructions for voice calls.
denoising_modeNoAudio denoising. The aggressive mode helps callers in cars/cafes (small surcharge).
max_silence_msNoHang up after this many ms of caller silence. Default 600000 (10 min).
transfer_numberNoPhone number to transfer calls to (E.164 format). Enables call transfer during conversations.
enable_messagingNoWhether a hosted agent can send and read texts during a call. Default true.
voicemail_messageNoVoicemail greeting text. When set, unanswered calls hear this message and can leave a voicemail.
enable_backchannelNoWhether the agent interjects 'uh-huh'/'mhmm' while the caller speaks. Default true.
interruption_sensitivityNoHow easily callers can interrupt (barge in). 0 = never, 1 = at first sound. Default 0.8.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations, so the description carries full disclosure burden. It usefully reveals that a newly created agent has no phone number until attached and clarifies the voice_mode branching, but says nothing about permissions, side effects, or what the creation returns — significant gaps for an 18-parameter mutation.

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 sentences, front-loaded with the core action, then the phone-number caveat, then mode selection. Zero waste and well ordered for scanning.

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?

Given no output schema and no annotations, the description covers the key branching decision (hosted vs webhook) and the post-creation prerequisite (attach a number). It could mention the response shape or default behavior, but it is adequate for an agent to invoke correctly.

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 the schema already documents all 18 parameters thoroughly. The description reinforces the voice_mode/system_prompt relationship but adds little beyond what the schema states. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Create a new agent') and adds real domain context — an agent owns phone numbers and handles calls/SMS. This distinguishes it from list_agents/update_agent/get_agent, though it does not explicitly name a sibling.

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 actionable mode-selection guidance: 'hosted' with a system_prompt for autonomous AI calls, or 'webhook' (default) to forward transcripts. It also implies the follow-up step (attach_number) by noting a new agent has no phone number. No explicit when-not or sibling routing, but clear context.

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