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

ghl-mcp-server-v2

by zackscriven

ghl_user_delete

DestructiveIdempotent

Deletes a GoHighLevel user by userId, enabling removal of an Agency or Sub-Account user account when users.write scope is available.

Instructions

KNOWN ISSUE: the official spec omits userId from this operation's path-parameter list (only the GET sibling declares it, despite all three sharing the same {userId} path template), so this tool currently has no input field for userId and calls will fail with a missing-path-parameter error until the generator (src/registry.ts) is patched to infer path params from the URL template. Tracked in this file's notes. Delete User Endpoint: DELETE /users/{userId} (Version header: v3; source: v3/users-v3.json) Requires an Agency or Sub-Account token. OAuth scopes: users.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": {
      "userId": "<userId>"
    },
    "name": "ghl_user_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
userIdYesPath parameter (inferred from the URL template; the official spec omits its declaration).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered structurally. The description adds useful auth scope and API version context, but its headline claim that the tool 'currently has no input field for userId' is stale and contradicts the shipped schema, which could cause an agent to wrongly skip a callable tool.

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?

Roughly half the text is an internal generator-bug note referencing src/registry.ts, which is implementation trivia for the tool author rather than guidance for a caller. The useful content (endpoint, auth, scope) is pushed behind it instead of being front-loaded.

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?

Annotations carry the destructive/idempotent profile and no output schema is needed for a delete, so the bar is moderate. The description covers auth and endpoint but omits what happens to the deleted user's associated data, and its central warning is out of date relative to the schema.

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

Parameters2/5

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

Schema coverage is 100% and the single userId parameter is documented as inferred from the URL template, so the schema alone would merit a 3. The description actively undermines that by asserting no userId input exists — a direct conflict with the required parameter in the schema — rather than clarifying its format or whether the value is a user ID or location-scoped identifier.

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 states a specific verb+resource ('Delete User') and pins the exact endpoint ('DELETE /users/{userId}'), which cleanly separates it from ghl_user_get, ghl_user_update, and ghl_user_create. The only weakness is that the actual purpose statement is buried behind a long bug-tracking paragraph rather than being front-loaded.

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?

The description gives real preconditions — 'Requires an Agency or Sub-Account token' and 'OAuth scopes: users.write' — which tells the agent whether it has the authority to call this. However, it never says when to prefer deletion over alternatives or what to check before deleting a user.

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