Skip to main content
Glama

Open or close the app

appUsersSetPrivate
Idempotent

Choosing who can open an app is appSharingSetMode’s; this older Private switch only puts a static-hosted app behind one-time invite links. It changes what visitors get, and requires confirmed: true, representing the human’s agreement to this exact setting for this exact app; without the literal nothing is sent. private: true gates the app’s address: only a request carrying its pass (set by opening an invite link) is served, and everyone else gets the door page; private: false opens it to everyone again. Only Tofu’s static hosting has the gate: turning it on for a server-hosted app is refused without saying why, and nothing changes. It takes effect right away when its answer says so, otherwise with the app’s next deployment: until then the version that is live keeps serving its side of the gate. An error result alone does not establish the app’s current Private setting. message says what happened: an app set to people or code can answer unchanged and stay restricted.

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>",
      "private": "<private>",
      "confirmed": "<confirmed>"
    },
    "name": "appUsersSetPrivate"
  }
}

Input Schema

NameRequiredDescriptionDefault
privateYes
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
messageYes
outcomeYes
privateYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=true), it discloses the confirmation gate ("without the literal nothing is sent"), the timing of effect (immediate when the answer says so, otherwise at next deployment, with the live version still serving its side of the gate), the silent refusal for non-static hosting, and the fact that an error alone does not establish current state. The `unchanged` outcome for already-restricted apps is a real behavioral nuance an agent could not infer.

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 differentiation from `appSharingSetMode` is front-loaded, which is right, and most sentences carry unique information. However, the prose is densely tangled ("Choosing who can open an app is appSharingSetMode's") and the timing/deployment material is packed into one long sentence rather than being structured, making it harder to parse than its length alone would suggest.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, yet the description still clarifies what `message` means, including the `unchanged` case. Combined with the confirmation requirement, deployment-dependent timing, and the silent refusal path, an agent has everything needed to call this correctly and interpret the outcome.

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 description coverage is 0%, so the description carries the full burden and largely does: `private: true` gates the address so only a request with the invite-issued pass is served and everyone else gets the door page, `private: false` reopens it, and `confirmed` must be the literal true representing human agreement. `projectId` is left unexplained, which is the only real gap for a 3-parameter tool.

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 concrete effect: it puts a static-hosted app behind one-time invite links (`private: true`) or opens it to everyone (`private: false`). It explicitly carves out the sibling `appSharingSetMode` as the tool for choosing who can open an app, so the agent can separate the two without opening either schema. The framing is indirect (it defines itself by what it is not first), which keeps it from a 5.

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 names the alternative explicitly ("Choosing who can open an app is appSharingSetMode's") and gives a hard exclusion: turning the gate on for a server-hosted app is refused and nothing changes. It also states the `confirmed` precondition tied to human agreement. It stops short of spelling out the exact scenario in which an agent should pick this legacy switch over the modern one, leaving part of the routing to inference.

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