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

ghl-mcp-server-v2

by zackscriven

ghl_conversation_update_email_message_status

Idempotent

Update the delivery status, per-recipient outcomes, and event counters for emails sent through a custom conversation provider. Use it to record opens, clicks, failures, and overall message status.

Instructions

Update email message status Update delivery events, per-recipient statuses, and the overall message status for an email sent via a custom conversation provider.

Authorization

  • Requires the conversations/message.write OAuth scope.

  • The calling OAuth app must own the conversation provider that originally sent the email.

  • Attempts to update emails sent via LC Email or Mailgun will return 403 Forbidden.

Updatable Fields

All request body fields are optional. Pass only what you need to update.

events — Aggregate delivery event counters (integers). Counters are merged into the existing values (not replaced). Setting a counter to 0 is treated as no-op and will not reset the stored value.

recipients — Per-recipient delivery statuses. Each entry maps a recipient email address to a MessageStatus value. Use failReason to capture bounce or rejection details when the status is failed.

status — The overall message status. Accepts any MessageStatus enum value.

Event Inference

The API automatically infers related events to maintain data consistency:

  • clicked, complained, unsubscribed, or replied → implies opened (set to 1 if not already provided and open tracking is enabled) and delivered (set to 1).

  • opened → implies delivered (set to 1 if not provided).

  • delivered, permanent_fail, or temporary_fail → implies accepted (set to 1 if not provided).

Timestamps

The API automatically records server-side timestamps on first oc Endpoint: PUT /conversations/messages/email/{emailMessageId}/status (Version header: v3; source: v3/conversations-v3.json) OAuth scopes: conversations/message.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": {
      "emailMessageId": "<emailMessageId>",
      "body": "<body>"
    },
    "name": "ghl_conversation_update_email_message_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body to update the delivery status of an email message. `status` is required. `events` and `recipients` are optional and may be included together with `status`. - Use `events` to report aggregate delivery metrics (delivered count, open count, etc.). - Use `recipients` to track per-recipient delivery outcomes for multi-recipient emails. - Use `status` to set the overall message status. Multiple calls are additive — event counters are merged, recipient statuses are upserted, and the message status is overwritten.
emailMessageIdYesEmail Message Id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv2.1.0
    • changedInput schema / properties / body / properties / events / allOf
      Previous value: -[
      -  {
      -    "additionalProperties": {
      -      "description": "Additional provider event counter (merged into stored values).",
      -      "type": "integer"
      -    },
      -    "description": "Aggregate delivery event counters for the email message. Values are merged into existing stored counters (additive update, not replacement). A value of `0` is treated as a no-op and will not reset the stored counter. Only include fields you want to update. Provider-specific counters such as `permanent_fail`, `temporary_fail`, and `esp_isp_block` may be sent using those snake_case keys.",
      -    "properties": {
      -      "accepted": {
      -        "description": "Number of messages accepted by the receiving mail server for delivery. Automatically inferred (set to 1) when `delivered`, `permanent_fail`, or `temporary_fail` events are reported.",
      -        "example": 1,
      -        "type": "integer"
      -      },
      -      "clicked": {
      -        "description": "Number of link click events within the email body. Triggers automatic inference of both `opened` and `delivered`.",
      -        "example": 1,
      -        "type": "integer"
      -      },
      -      "complained": {
      -        "description": "Number of spam complaint events (e.g., recipient marked the email as spam). Triggers automatic inference of `opened` and `delivered`.",
      -        "example": 0,
      -        "type": "integer"
      -      },
      -      "delivered": {
      -        "description": "Number of successful deliveries — the recipient mail server accepted the message. Automatically inferred (set to 1) when `opened`, `clicked`, `complained`, `unsubscribed`, or `replied` events are reported.",
      -        "example": 1,
      -        "type": "integer"
      -      },
      -      "failed": {
      -        "description": "Total number of delivery failures (includes both permanent and temporary). For more granular failure tracking, use `permanent_fail` and `temporary_fail` instead.",
      -        "example": 0,
      -        "type": "integer"
      -      },
      -      "opened": {
      -        "description": "Number of unique open events (typically tracked via a tracking pixel). Automatically inferred (set to 1) when `clicked`, `complained`, `unsubscribed`, or `replied` events are reported, provided open tracking is enabled on the email.",
      -        "example": 3,
      -        "type": "integer"
      -      },
      -      "rejected": {
      -        "description": "Number of messages rejected outright by the receiving mail server (before acceptance).",
      -        "example": 0,
      -        "type": "integer"
      -      },
      -      "replied": {
      -        "description": "Number of reply events. Triggers automatic inference of both `opened` (if open tracking is enabled) and `delivered`.",
      -        "example": 1,
      -        "type": "integer"
      -      },
      -      "stored": {
      -        "description": "Number of messages stored by the email service provider (ESP-specific event).",
      -        "example": 0,
      -        "type": "integer"
      -      },
      -      "unsubscribed": {
      -        "description": "Number of unsubscribe events triggered by the recipient. Triggers automatic inference of `opened` and `delivered`.",
      -        "example": 0,
      -        "type": "integer"
      -      }
      -    },
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {
      +      "description": "Additional provider event counter (merged into stored values).",
      +      "type": "integer"
      +    },
      +    "description": "Aggregate delivery event counters for the email message. Values are merged into existing stored counters (additive update, not replacement). A value of `0` is treated as a no-op and will not reset the stored counter. Only include fields you want to update. Provider-specific counters such as `permanent_fail`, `temporary_fail`, and `esp_isp_block` may be sent using those snake_case keys.",
      +    "properties": {
      +      "accepted": {
      +        "description": "Number of messages accepted by the receiving mail server for delivery. Automatically inferred (set to 1) when `delivered`, `permanent_fail`, or `temporary_fail` events are reported.",
      +        "example": 1,
      +        "type": "integer"
      +      },
      +      "clicked": {
      +        "description": "Number of link click events within the email body. Triggers automatic inference of both `opened` and `delivered`.",
      +        "example": 1,
      +        "type": "integer"
      +      },
      +      "complained": {
      +        "description": "Number of spam complaint events (e.g., recipient marked the email as spam). Triggers automatic inference of `opened` and `delivered`.",
      +        "example": 0,
      +        "type": "integer"
      +      },
      +      "delivered": {
      +        "description": "Number of successful deliveries — the recipient mail server accepted the message. Automatically inferred (set to 1) when `opened`, `clicked`, `complained`, `unsubscribed`, or `replied` events are reported.",
      +        "example": 1,
      +        "type": "integer"
      +      },
      +      "failed": {
      +        "description": "Total number of delivery failures (includes both permanent and temporary). For more granular failure tracking, use `permanent_fail` and `temporary_fail` instead.",
      +        "example": 0,
      +        "type": "integer"
      +      },
      +      "opened": {
      +        "description": "Number of unique open events (typically tracked via a tracking pixel). Automatically inferred (set to 1) when `clicked`, `complained`, `unsubscribed`, or `replied` events are reported, provided open tracking is enabled on the email.",
      +        "example": 3,
      +        "type": "integer"
      +      },
      +      "rejected": {
      +        "description": "Number of messages rejected outright by the receiving mail server (before acceptance).",
      +        "example": 0,
      +        "type": "integer"
      +      },
      +      "replied": {
      +        "description": "Number of reply events. Triggers automatic inference of both `opened` (if open tracking is enabled) and `delivered`.",
      +        "example": 1,
      +        "type": "integer"
      +      },
      +      "stored": {
      +        "description": "Number of messages stored by the email service provider (ESP-specific event).",
      +        "example": 0,
      +        "type": "integer"
      +      },
      +      "unsubscribed": {
      +        "description": "Number of unsubscribe events triggered by the recipient. Triggers automatic inference of `opened` and `delivered`.",
      +        "example": 0,
      +        "type": "integer"
      +      }
      +    },
      +    "title": "EmailEventsDto",
      +    "type": "object"
      +  }
      +]
    • addedInput schema / properties / body / properties / recipients / items / title
      Added value: +"UpdateRecipientMessageStatusDto"
    • addedInput schema / properties / body / title
      Added value: +"UpdateEmailMessageStatusDto"
    • addedInput schema / properties / emailMessageId
      Added value: +{
      +  "description": "Email Message Id",
      +  "example": "ve9EPM428h8vShlRW1KT",
      +  "type": "string"
      +}
    • removedInput schema / properties / id
      Removed value: -{
      -  "description": "Email message id",
      -  "example": "ve9EPM428h8vShlRW1KT",
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "id",
      -  "body"
      -]New value: +[
      +  "emailMessageId",
      +  "body"
      +]
  2. First observedv2.0.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only cover the safety profile (not read-only, idempotent, non-destructive, open-world); the description goes far beyond by disclosing merge-not-replace semantics, that a counter of 0 is a silent no-op, that recipients are upserted/overwritten, and a full event-inference table. That is exactly the operational context an agent needs and cannot get from the schema or annotations.

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?

Well front-loaded with markdown section headers (Authorization, Updatable Fields, Event Inference, Timestamps) so the agent can scan rather than parse prose. The one flaw is that the final Timestamps section is cut off mid-sentence ('records server-side timestamps on first oc'), leaving dangling content.

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 mutation endpoint with a nested body, two required params, and no output schema, the description covers auth, merge semantics, and inference thoroughly. The truncated timestamps section is the only real hole, and it is a small one given no return value needs explaining.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning the schema alone would bury: that counters merge rather than replace, that 0 will not reset a stored counter, and that failReason should accompany a failed recipient status. The event-inference rules also change how an agent should choose which counters to send.

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

Purpose5/5

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

The opening line names the exact verb and object ('Update email message status') and immediately enumerates the sub-resources touched: delivery events, per-recipient statuses, and overall message status. The scope restriction 'for an email sent via a custom conversation provider' plus the 403 note about LC Email/Mailgun cleanly separates it from the generic sibling ghl_conversation_update_message_status.

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?

It gives strong usage conditions: the required OAuth scope, the provider-ownership precondition, and the exact failure case (403 for LC Email/Mailgun sends). It stops short of naming a concrete alternative tool for those excluded cases, so the agent must infer where to go instead.

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