Skip to main content
Glama

Create an invite link

appInvitesCreate

Create an invite link that lets ONE person into one owned PRIVATE app, whose door answers everyone else. Requires confirmed: true, representing the human’s agreement to hand a way into THIS app to somebody; without the literal nothing is created. The app must be private through its older Private setting (read appInvitesList: private true — otherwise turn Private on first on the Sign-in page) and live on Tofu’s static hosting, with sharing not set to people or code (appSharingGet); any other app is refused without saying which condition failed. Creating a link changes nothing about the app — nobody is let in until someone opens it — and Tofu sends the person nothing itself. The answer’s invite.url is the link the human sends to the one person: the first time it is opened it admits them and stops working for anyone else. Every call mints another link; an error result alone does not establish whether one was minted, and appInvitesList reports what each call left behind.

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>",
      "confirmed": "<confirmed>"
    },
    "name": "appInvitesCreate"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmedYes
projectIdYes
expiresInDaysNo

Output Schema

NameRequiredDescriptionDefault
inviteYes
messageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations it discloses that the call changes nothing about the app and admits nobody until the link is opened, that Tofu sends no notification, that refusals are silent as to which precondition failed, that every call mints another link, and that an error result does not prove whether a link was minted. The last point is exactly the ambiguity an agent needs to know to verify via appInvitesList, and it is consistent with idempotentHint=false.

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?

Front-loaded with purpose, then prerequisites, then side-effect semantics — a sensible order with no filler sentences. Some clauses are needlessly indirect ("whose door answers everyone else," "the literal"), which costs a little parsing effort.

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?

With an output schema present, the description only needs to flag the meaningful return field, and it does (`invite.url` is the human-delivered link that admits the first opener and then stops working). Non-idempotency, refusal behavior, and lack of side effects are covered; only the expiry parameter's meaning is missing.

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

Parameters3/5

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

Schema coverage is 0%, so the description must carry parameter meaning; it fully explains `confirmed` (must be literal true, representing human agreement) and implicitly ties projectId to the qualifying private app. However, `expiresInDays` is never mentioned, leaving the link's validity window undocumented anywhere — a meaningful gap for a tool whose output is a one-time credential.

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?

States a specific verb and resource (create an invite link) and immediately narrows scope: ONE person, one owned PRIVATE app, one-time use. That is enough for an agent to distinguish it from appInvitesList (reporting) and appInvitesRevoke (withdrawal) without opening either schema.

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 concrete call prerequisites (confirmed: true, app private via the older Private setting, static hosting, sharing not set to people or code) and names the sibling checks to run beforehand (appInvitesList, appSharingGet, Sign-in page). It does not compare against other ways of admitting users (appSharingAddPeople, appSharingNewCode), so the agent must infer that this is the single-person path.

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