Skip to main content
Glama

Remove app user

appUsersRemove
DestructiveIdempotent

Remove ONE person from one owned app (Sign-in page): their account in the app’s own sign-in service is deleted, which signs them out — a page they already have open may keep working for up to an hour. Requires userId exactly as appUsersList returned it and confirmed: true, representing the human’s agreement to remove this exact person from this exact app; without the literal nothing is sent. It cannot be undone and never touches a Tofu account. Afterwards they cannot get back in while sign-up is invited unless added again; while it is anyone they could sign up again. Their rows in tables appUsersList reports as deleted go with the account. A table that blocks makes the outcome blocked, nothing changed: their records there must be deleted or reassigned first, a change to the app itself. not_found changed nothing, so repeating a removal is safe. message is Tofu’s own sentence for the outcome. An error result alone does not establish whether removal was applied.

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": {
      "projectId": "<projectId>",
      "userId": "<userId>",
      "confirmed": "<confirmed>"
    },
    "name": "appUsersRemove"
  }
}

Input Schema

NameRequiredDescriptionDefault
userIdYes
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
personYes
messageYes
outcomeYes
blockedByYes
signupModeYes
removedWithYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond annotations already marking this destructive and idempotent, the description adds detailed behavioral consequences: account deletion, sign-out, possible continued access for up to an hour, irreversibility, table-row effects, blocked outcomes, and safe repetition after not_found. It also warns that an error alone does not establish whether removal happened.

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?

The description is front-loaded with the action and primary effect, and most clauses earn their place by covering destructive consequences and edge cases. It is dense as a single paragraph with semicolon-separated clauses, which slightly reduces readability.

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 destructive tool with an output schema and rich annotations, it covers prerequisites, consequences, idempotency, blocked records, and outcome ambiguity thoroughly. The main missing piece is any explicit explanation of projectId semantics.

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?

With 0% schema description coverage, the description compensates well for userId by requiring it exactly as appUsersList returned it, and for confirmed by defining it as literal human agreement. It does not explicitly explain projectId, which is the remaining gap.

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 description states a precise verb and resource: remove ONE person from one owned app's sign-in service, and it explicitly distinguishes the effect from Tofu account removal. It is clear this is not listing, adding, or sharing management.

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 context: the exact userId source, the human-confirmation requirement, irreversibility, and sign-up-mode consequences. It does not explicitly compare this tool to sibling alternatives for removing or managing app users, so it falls short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources