Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_conversation_ai_create_agent

Create a new AI agent for a location by defining its name, personality, goal, instructions, channels, and response behavior. Use it to configure conversation automation for customer inquiries.

Instructions

Create an Agent Creates a new AI agent for the location. The agent will be created with the specified configuration including name, role, actions, and behavior settings. Endpoint: POST /conversation-ai/agents (Version header: v3; source: v3/conversation-ai-v3.json) OAuth scopes: conversation-ai.write

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": {
      "body": "<body>"
    },
    "name": "ghl_conversation_ai_create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.1.0
    • changedInput schema / properties / body / properties / channels / items / enum
      Previous value: -[
      -  "IG",
      -  "FB",
      -  "SMS",
      -  "WebChat",
      -  "WhatsApp",
      -  "Live_Chat"
      -]New value: +[
      +  "IG",
      +  "FB",
      +  "SMS",
      +  "WebChat",
      +  "WhatsApp",
      +  "Live_Chat",
      +  "Email"
      +]
    • addedInput schema / properties / body / properties / fullPrompt
      Added value: +{
      +  "description": "Complete agent prompt. When set and non-empty, used as the source of truth at generation time instead of personality, goal, and instructions.",
      +  "type": "string"
      +}
    • addedInput schema / properties / body / properties / knowledgeBaseIds / example
      Added value: +[
      +  "kb_abc123",
      +  "kb_def456"
      +]
    • addedInput schema / properties / body / title
      Added value: +"CreateEmployeeDto"
  2. First observedv2.0.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the mutation profile is covered. The description adds genuinely useful non-annotation context: the exact endpoint, API version header, and required OAuth scope (conversation-ai.write). It does not, however, warn that retries create duplicate agents (non-idempotent) or indicate whether location-level limits/permissions apply.

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?

Front-loaded with the action, then supporting detail, then structured endpoint/scope metadata. Slightly redundant ("Create an Agent" title plus "Creates a new AI agent"), and the "role, actions" clause is wasted words that misdirect.

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?

Auth scope and endpoint are well covered, and the rich body schema handles inputs. But there is no output schema and the description says nothing about the response – notably that the tool presumably returns the new agent's ID needed for subsequent update/get/working-hours calls. For a create operation in a multi-step workflow, that omission matters.

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% with 20 well-documented nested fields (including defaults, enums, and deprecation notes), so the schema carries the parameter burden. The description adds no field-level meaning beyond a vague mention of name/role/actions/behavior, and its mention of "role" is not backed by any parameter.

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 ("Creates a new AI agent for the location") that is clearly distinguishable from siblings like ghl_conversation_ai_update_agent or ghl_voice_ai_create_agent. However, the claim that the configuration includes "role, actions" is imprecise – the body schema has no role or action fields (actions are a separate resource), which could send an agent looking for parameters that don't exist.

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

Usage Guidelines2/5

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

No statement of when to use this versus alternatives. With siblings like ghl_conversation_ai_update_agent, ghl_conversation_ai_create_action, and the voice-AI create_agent in the toolset, an explicit differentiation (conversation AI vs voice AI, agent vs action) would have been valuable. The OAuth scope line implies a write prerequisite but nothing more.

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