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

ghl-mcp-server-v2

by zackscriven

ghl_conversation_ai_update_agent

Idempotent

Updates an existing Conversation AI agent's configuration, including name, status, channels, goal, prompt, and behavior settings, so you can change how the agent responds and operates.

Instructions

Update Agent Updates an existing AI agent's configuration. All fields in the agent configuration can be updated including name, status, actions, and behavior settings. Endpoint: PUT /conversation-ai/agents/{agentId} (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": {
      "agentId": "<agentId>",
      "body": "<body>"
    },
    "name": "ghl_conversation_ai_update_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).
agentIdYesConversations AI agent id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv2.1.0
    • addedInput schema / properties / agentId / example
      Added value: +"ve9EPM428h8vShlRW1KT"
    • addedInput schema / properties / body / properties / autoPilotMaxMessages / example
      Added value: +75
    • addedInput schema / properties / body / properties / channels / example
      Added value: +[
      +  "SMS",
      +  "Live_Chat"
      +]
    • 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 / properties / mode / example
      Added value: +"auto-pilot"
    • addedInput schema / properties / body / properties / sleepTimeUnit / example
      Added value: +"hours"
    • addedInput schema / properties / body / title
      Added value: +"UpdateEmployeeDto"
  2. First observedv2.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly=false, idempotent=true, destructive=false, and openWorld=true; the description adds genuinely new operational context — the OAuth scope conversation-ai.write and the v3 version header — which helps an agent reason about authorization failures. It does not, however, clarify whether this PUT replaces the whole configuration or merges, which matters for a mutation with a required field (autoPilotMaxMessages).

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?

Purpose is front-loaded in one sentence, followed by compact metadata lines (endpoint, spec source, OAuth scope) that each carry information. The leading 'Update Agent' restates the tool name and is the only real waste.

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 two-parameter mutation with a deeply nested body, the schema carries the field-level burden and the annotations carry the safety profile, so the description only needs to add auth and endpoint context — which it does. The remaining gap is the replace-vs-merge PUT semantics and expected response shape, though no output schema exists to lean on.

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 every parameter and nested body field is already documented in the schema; the baseline of 3 applies. The description's field list ('name, status, actions') does not map cleanly onto the actual body properties (no 'status' or 'actions' keys exist in the schema), adding a touch of noise rather than meaning.

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 names a specific verb and resource ('Updates an existing AI agent's configuration') and enumerates the kinds of fields affected (name, status, actions, behavior settings). The word 'existing' plus the PUT endpoint distinguishes it from the sibling ghl_conversation_ai_create_agent, though no sibling is named explicitly.

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?

Usage is only implied: an agent can infer 'use when modifying an existing agent,' but there is no explicit guidance about when to use this vs. ghl_conversation_ai_create_agent, ghl_conversation_ai_update_action, or ghl_conversation_ai_update_agent_working_hours, and no note about prerequisites like having an agentId from a list/search call.

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