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

ghl-mcp-server-v2

by zackscriven

ghl_conversation_live_chat_agent_typing

Sends a typing indicator for a live chat conversation, letting an agent or AI bot show a visitor that a reply is being composed.

Instructions

Agent/Ai-Bot is typing a message indicator for live chat Agent/AI-Bot will call this when they are typing a message in live chat message Endpoint: POST /conversations/providers/live-chat/typing (Version header: v3; source: v3/conversations-v3.json) Requires a Sub-Account (location) token. OAuth scopes: conversations/livechat.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_live_chat_agent_typing"
  }
}

Input Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.1.0
    • changedInput schema / properties / body / properties / visitorId / description
      Previous value: -"Unique ID assigned to each live chat visitor."New value: +"visitorId is the Unique ID assigned to each Live chat visitor. visitorId will be added soon in <a href=\"../contacts/get-contact\" target=\"_blank\">GET Contact API</a>"
    • addedInput schema / properties / body / title
      Added value: +"UserTypingBody"
  2. First observedv2.0.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare this as a non-readonly, non-idempotent, open-world write with destructiveHint=false, so the safety profile is known. The description adds genuinely useful context beyond that: a Sub-Account (location) token is required and the OAuth scope conversations/livechat.write is needed. However, it omits the behavior that matters most for a typing indicator — whether the state auto-expires or must be explicitly turned off.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The opening two sentences say largely the same thing ('is typing a message indicator' / 'will call this when they are typing'), so the header is redundant rather than front-loaded. The endpoint, token, and scope lines do earn their place, but the duplication costs it a point on an otherwise short description.

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?

Endpoint, version header, source spec, token type, and OAuth scope are all supplied, and the body schema is fully self-documenting with no output schema needed for what is essentially a fire-and-forget signal. The only meaningful gap is what the indicator's lifecycle looks like (expiry vs. explicit clear), which an agent would otherwise have to guess.

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 a fully documented nested body (locationId, visitorId, conversationId, isTyping), so the schema carries parameter meaning. The description adds nothing about the body — notably it never clarifies that isTyping is a toggle used both to start and stop the indicator. Baseline 3 applies since the schema does the work.

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 the specific effect (a typing indicator for a live-chat visitor) and grounds it with the concrete endpoint POST /conversations/providers/live-chat/typing. The phrasing 'Agent/Ai-Bot is typing a message indicator' is grammatically clumsy and never states the actual action (set/clear typing status), but the resource and scope are unmistakable and no sibling tool competes for this niche.

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?

'Agent/AI-Bot will call this when they are typing a message in live chat' gives an implied trigger condition, but it is circular — it restates the tool's own name rather than telling the agent when in a workflow to emit or clear the indicator. There is no guidance on whether to also send isTyping=false afterwards, nor on any alternative sibling tool for messaging.

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