Skip to main content
Glama

Invite people

invite_users

Invite people into this Project by email, all into every Role named plus Member. With no Roles named, they hold Member. Ekaya Central previews seats first; invitations are sent only when that preview adds no billable seat: a new seat among the seats the plan includes changes no bill and is sent without confirmation. Central decides seats and charges at send time; a concurrent invitation can still make the send add a billable seat. If the preview adds billable seats, or states no charge figures, sends nothing and returns seat_purchase_requires_confirmation with the preview and human_link to Roles and Members. Give that link to the person so an Administrator can review and confirm the purchase. Each sent address is reported as invited, already_member or already_invited. An invited person holds those Roles from invitation onward. At most 50 addresses at a time. Administrators take no seat and need no Team upgrade or seat confirmation. Ekaya Solo includes one User; every further User requires Ekaya Team. Check list_users invitation_eligibility before preparing Roles or app access — a team_required result is reported unrestricted for Administrator invitations and never refuses them. Eligibility is checked again on every invitation.

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": {
      "emails": "<emails>"
    },
    "name": "invite_users"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailsYesEmail addresses to invite
role_idsNoUUIDs of the Roles every invited person will hold in addition to Member; omitted or empty means Member

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes far beyond the annotations: explains the seat-preview gate, the concurrent-invitation race that can still incur a charge, that nothing is sent on refusal, the per-address outcome values (invited, already_member, already_invited), the 50-address cap, and that eligibility is re-checked on every call. These are exactly the side effects and limits an agent needs for a non-idempotent, open-world mutation, and they are consistent with destructiveHint=false and 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-loads the action in the first sentence and then layers billing/confirmation detail that genuinely matters for calling it correctly. It is dense and runs long for a two-parameter tool, with the Member fallback stated twice and the Administrator exemption dropped in mid-paragraph rather than grouped with the seat rules.

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?

Although there is no output schema, the description documents the return outcomes, the refusal status and its payload, the size limit, the eligibility prerequisite, and the plan-tier constraint (Solo one User, further Users require Team). Nothing an agent needs to invoke this safely or interpret the result is missing.

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 coverage is 100%, so the baseline is 3; the description nonetheless adds a real constraint not present in the schema — 'At most 50 addresses at a time' for emails. The role_ids explanation ('all into every Role named plus Member') largely restates the schema's own 'in addition to Member; omitted or empty means Member', which limits the added value.

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?

Opens with a specific verb and resource: 'Invite people into this Project by email,' plus the role assignment semantics. It distinguishes itself from add_role_members by scope (a Role's existing members vs. new invitees) and references list_users for the pre-check, though that differentiation is implied rather than stated as an explicit 'use X instead'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States precisely when invitations actually send (only when the seat preview adds no billable seat) and when they will not (billable seats or no charge figures), naming the returned status seat_purchase_requires_confirmation and the human_link handoff. It also gives a prerequisite ('Check list_users invitation_eligibility before preparing Roles') and the Administrator exemption, so the agent knows both when to call and what to do on refusal.

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