Skip to main content
Glama

Invite user

invite_user
Destructive

Invite a person to join your organization by email at a chosen role. The organization is fixed by your context - never pass an organization id. Valid roles: Admin, Finance, Manager, Member, Viewer (you can only invite at a role no more privileged than your own). Once the user confirms, the invitation is created and the invitee is emailed an acceptance link. The result's mail_sent says whether that email went out: say the invitation was emailed ONLY when mail_sent is true. When mail_sent is false the invitation exists but its email could not be sent - say so, and that an admin can resend it or copy its link from the Users page.

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": {
      "email": "<email>",
      "role": "<role>"
    },
    "name": "invite_user"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleYesRole to grant on acceptance (required). One of: Admin, Finance, Manager, Member, Viewer. You cannot invite at a role more privileged than your own.
emailYesEmail address of the person to invite (required).
idempotency_keyNoOptional caller-supplied key; retrying with the same key returns the original result instead of acting twice.

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?

Goes well beyond the annotations (which only state it is mutating, open-world, non-idempotent and destructive) by describing the state change: the invitation is created and an acceptance email is dispatched, and it explains how to interpret mail_sent and what to tell the user when the email fails. This is exactly the kind of outcome and failure-mode context that structured fields cannot carry.

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 constraints, then result handling; every sentence carries operational value except the role enumeration, which duplicates the schema enum. Slightly long but well ordered.

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?

No output schema exists, and the description compensates by explaining the meaningful field of the result (mail_sent) and what to do when it is false. For a 3-parameter mutating tool with full schema coverage, nothing an agent needs in order to call and report correctly 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 100%, so the enum of roles and the email meaning are already documented in the schema and the description largely repeats the role list. The one piece of added meaning is the privilege ceiling on the role parameter, which the schema also mentions; the idempotency_key parameter is not discussed in the description at all.

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?

Specific verb plus resource plus scope: 'Invite a person to join your organization by email at a chosen role.' It is immediately distinguishable from cancel_invite/resend_invite because it clearly creates a new invitation, and the org-from-context constraint further pins down what the tool does.

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 preconditions for use: the organization is fixed by context and must never be passed, and the inviter can only grant a role no more privileged than their own. It does not explicitly route to sibling tools (e.g. resend_invite for resending, cancel_invite for undoing), referring instead to admin actions in the UI, so the when-not guidance is slightly incomplete.

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