Skip to main content
Glama

Choose who can open an app

appSharingSetMode
DestructiveIdempotent

Choose who can open one of your apps (Share & access page): make it private — open only to people you choose by email, or to anyone with an access code — or open it to anyone with the link. With people, emails adds those people in the same call. Requires confirmed: true, representing the human’s agreement to this exact setting for this exact app, made knowing that people or code puts Tofu’s sign-in page in front of the whole app at once: everyone not let in, including people using it now, sees it until link is chosen again; without the literal nothing is sent. If the answer is not changed or unchanged, an app that was open may still be open to anyone with the link.

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>",
      "mode": "<mode>",
      "confirmed": "<confirmed>"
    },
    "name": "appSharingSetMode"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
emailsNo
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
stateYes
messageYes
outcomeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag destructiveHint and idempotentHint, but the description goes well beyond them: it discloses the blast radius ('puts Tofu's sign-in page in front of the whole app at once: everyone not let in, including people using it now, sees it until `link` is chosen again') and the failure mode ('without the literal nothing is sent'). It also defines what `confirmed` actually attests to — a human's agreement to this exact setting for this exact app — which is the kind of consent semantics annotations cannot express.

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?

Purpose is correctly front-loaded, but the body is a single dense sentence chain stitched with em-dashes and colons that is hard to parse on first read. The closing line ('If the answer is not `changed` or `unchanged`, an app that was open may still be open to anyone with the link') is cryptic — it refers to return values that are never introduced — and would be clearer as a separate, plainly worded caveat.

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, open-world mutation with a consent gate, the definition covers consequences, prerequisites, and mode semantics thoroughly, and the existing output schema means return values need not be described. The one gap is that the final sentence leans on `changed`/`unchanged` result states without naming them as outputs, which slightly muddies an otherwise complete picture.

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 must carry the load, and it mostly does: it defines all three `mode` values, explains that `emails` only takes effect alongside `people`, and spells out the `confirmed` gate. `projectId` is never explained, and `emails` constraints (1–50 valid addresses) are left to the schema, but the semantic gap is largely closed.

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?

Names a specific verb+resource ('Choose who can open one of your apps') and then enumerates all three modes with their exact meanings — private by email, private by access code, or open to anyone with the link. An agent can map `mode: link|people|code` to real behavior without opening the schema, and the framing ('Share & access page') anchors it against siblings like appSharingAddPeople or appSharingNewCode.

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?

Gives clear conditions for each mode and an explicit prerequisite ('Requires `confirmed: true`'), plus a conditional rule for when `emails` applies ('With `people`, `emails` adds those people in the same call'). It never explicitly excludes alternatives — e.g. it does not say to use appSharingAddPeople when you only want to add people without changing mode — so the when-not guidance is left implicit.

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