Skip to main content
Glama

List app users

appUsersList
Read-onlyIdempotent

Read who can sign in to one owned app — the people with an account in its OWN sign-in service, never Tofu accounts: a page of them, newest first. total counts everyone; while hasMore is true, a later offset reads more. signupMode is null when it could not be read, which is an unknown state. accountLinks names the app’s own tables that point at accounts and what removing someone does to their rows (deleted, cleared, or blocks the removal); a removal is agreed only after the human has heard these effects. The answer’s message and nextSteps say what its state means and any next step: ready is a live read, not_ready means the app has no ready database yet (people sign in through it), and unavailable means the read produced NOTHING — never that nobody can sign in. The email addresses are the owner’s private data. It writes nothing and returns no password, token or credential.

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>"
    },
    "name": "appUsersList"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
offsetNo
projectIdYes

Output Schema

NameRequiredDescriptionDefault
limitYes
rolesNo
stateYes
totalYes
offsetYes
peopleYes
hasMoreYes
messageYes
privateYes
nextStepsYes
signupModeYes
accountLinksYes

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?

Goes well past the annotations: it defines the tri-state outcome (`ready` = live read, `not_ready` = no ready database, `unavailable` = the read produced NOTHING, explicitly not 'nobody can sign in'), explains that `signupMode` null is an unknown state rather than a value, and flags that `email` addresses are the owner's private data. It also pre-describes what removal does to linked rows (`deleted`, `cleared`, `blocks`), which is behavior an agent needs before touching a mutating sibling.

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?

Well front-loaded — the first clause says exactly what is listed and what is excluded — and every subsequent sentence carries distinct information. It is dense and clause-heavy, packing several concepts into single sentences, which slows parsing but doesn't produce filler.

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?

Coverage is strong for a read tool with an output schema: pagination, state semantics, null handling, privacy, and the 'writes nothing / returns no credentials' guarantee are all addressed, so an agent can call it and interpret the response safely. The remaining gap is the unexplained required `projectId` and page-size limits.

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 description coverage is 0%, so the description has to carry the load; it does explain the `offset`/`hasMore`/`total` pagination contract and implies `limit` via 'a page of them'. However, `projectId` (the only required parameter) and the 1–100 / 0–100000 bounds are never mentioned, so roughly a third of the parameter surface is unexplained.

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 ('Read who can sign in to one owned app') and immediately bounds the scope ('the people with an account in its OWN sign-in service, never Tofu accounts'), which separates it from account-wide or invite-oriented siblings without opening any 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 clear operating context: read a page newest-first, keep calling with a later `offset` while `hasMore` is true, and treat `accountLinks` as the pre-flight check a human must approve before any removal. It never names a concrete alternative sibling (e.g. pending invites vs. existing accounts) or an explicit 'do not use this for X', so it stops short of a full when/when-not statement.

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