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

ghl-mcp-server-v2

by zackscriven

ghl_contact_create_task

Create a task linked to a specific contact by providing title, due date (ISO 8601), and completion status.

Instructions

REGRESSION-VERIFIED: assignedTo is present in CreateTaskParams. The old connector's create_task always 422'd — per the spec (v3/contacts-v3.json CreateTaskParams.required), title, dueDate, and completed are ALL required on create (not just title), and dueDate must be ISO 8601 (e.g. 2020-10-25T11:00:00Z). Passing completed:false is required even though it reads oddly for a brand-new task — that's what the spec mandates. Create Task Endpoint: POST /contacts/{contactId}/tasks (Version header: v3; source: v3/contacts-v3.json) OAuth scopes: contacts.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": {
      "contactId": "<contactId>",
      "body": "<body>"
    },
    "name": "ghl_contact_create_task"
  }
}

Input Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.0
    • addedInput schema / properties / body / title
      Added value: +"CreateTaskParams"
  2. First observedv2.0.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the description correctly doesn't restate them. It adds real context annotations cannot: the required OAuth scope contacts.write, the historical 422 failure mode, and the non-obvious requirement to send completed:false on create. Some of this is internal QA narrative rather than tool behavior, which keeps it from 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.

Conciseness2/5

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

The description leads with internal engineering meta-commentary ("REGRESSION-VERIFIED", "The old connector's create_task always 422'd") before stating what the tool does, which inverts the ideal front-loading and spends several sentences narrating a past bug rather than the current call contract.

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 with no output schema, the definition supplies endpoint, API version, auth scope, and the required field contract — enough to invoke it correctly. It does not say what the response contains (task ID, created object) or whether task creation triggers workflows, but those are minor for a 2-parameter mutation.

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, and the description clears that bar by emphasizing that title, dueDate, AND completed are all required — a constraint an agent could easily miss or second-guess from the schema alone — plus the ISO 8601 format expectation. It adds little on the nested body/assignedTo fields beyond what the schema already documents.

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?

"Create Task" plus the endpoint POST /contacts/{contactId}/tasks gives a specific verb and resource, and the path implicitly separates it from sibling task tools (ghl_project_create_list_task, ghl_location_create_recurring_task, ghl_contact_update_task). It stops short of explicitly naming those alternatives, so an agent must infer the distinction from the URL.

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: the endpoint tells the agent this creates a task attached to a contact. There is no statement of when to prefer this over ghl_contact_update_task or the project/recurring task creation siblings, and no prerequisites beyond the field requirements embedded in the regression note.

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