Skip to main content
Glama

Create an AI agent from a template

agent_create

Creates a new AI voice agent for this business from one of the starter templates, with the business's name, a language, optional extra languages the agent should also understand, and an optional custom greeting. The new agent answers no phone number until it is put on one. With dryRun: true (the default) it returns the name, greeting and instructions the agent would get and creates nothing. Tools such as calendar booking are added later in the portal.

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": {
      "template": "<template>",
      "business_name": "<business_name>"
    },
    "name": "agent_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe agent's name; defaults to the business name and template
dryRunNoIf true (default), only show what would be created
greetingNoThe first line the agent speaks; defaults to the template's
languageNoMain language code, e.g. en-IN (default) or hi-IN
templateYesThe template id, e.g. receptionist
business_nameYesThe business the agent speaks for
extra_languagesNoOther language codes callers may use, e.g. ["hi-IN"]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations, the description discloses that dryRun: true creates nothing and returns preview data, that the new agent answers no phone number until assigned, and that tools like calendar booking are added later in the portal. These are meaningful behavioral details for a write tool. It still does not clarify idempotency or error behavior, so it is not 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.

Conciseness4/5

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

The description is front-loaded with the core action and then adds key caveats about dry-run and phone-number assignment. The first sentence is long, but every sentence contributes relevant information. There is no filler.

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?

For a create tool without an output schema, the description covers what is created, the default preview behavior, and the fact that the agent is not yet attached to a phone number. Remaining gaps around permissions and failure modes are minor given the annotations and complete schema.

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 field descriptions already document defaults and formats for all seven parameters. The description adds conceptual context, such as the greeting being the first spoken line and extra_languages covering languages callers may use. This is useful but mostly overlaps the schema, fitting the baseline of 3.

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?

The description states a specific verb and resource: creates a new AI voice agent from a starter template for the business. It clarifies that the agent is unassigned to a phone number until explicitly put on one. It lacks explicit differentiation from siblings such as agent_update or agent_template_list, so it falls short of a 5.

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

Usage Guidelines3/5

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

The description implies usage by explaining that a template id is needed and that dryRun defaults to true. It does not state when to choose this tool over agent_update or agent_template_list. The guidance is adequate but mostly inferred.

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.