Skip to main content
Glama

Create an invite link

invite_create

Create a join link for a flat so people can become flatmates, since the share code alone cannot be used to join. Each link lasts 14 days and allows up to 10 joins.

Instructions

Create a link that lets one or more people join the flat; this is the only way to add flatmates, because the share code alone does not allow joining. The link works for 14 days and for up to 10 joins, and a flat holds at most 20 active links (invite_limit_reached; free one with invite_revoke). Use it when the user wants to hand the link over themselves; to send it by email use invite_email instead, to see existing links use invites_list. Any member may call it. Not idempotent: every call creates a new link. Returns id, url and expiresAt. url is a secret that lets anyone who has it join the flat, so show it only to the user and never post it in chat, notes or logs. It cannot be read again later, because invites_list never returns it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "invite_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
wgCodeNoShare code of the flat (code from wg_list). Leave it out when the account belongs to one flat.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, it discloses the 14-day/10-join validity window, the 20-active-link cap with the invite_limit_reached error and its remedy (invite_revoke), and that the call is non-idempotent with a new link each time. It describes the return payload (id, url, expiresAt) and the critical secret-handling constraint that url is unrecoverable because invites_list never returns it.

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?

Purpose, alternatives, limits and the security warning are ordered by importance and no sentence is filler. It is dense — several sentences pack multiple constraints into long clauses — which slightly raises reading load, but the information density is warranted.

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?

For a single-parameter creation tool with no output schema, it covers everything an agent needs: preconditions, capacity limits and error codes, non-idempotency, the shape of the return value, and how to handle the secret url. Nothing material 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?

The single parameter wgCode is fully documented in the schema, including the pattern, the wg_list source, and the omission rule for single-flat accounts, so the baseline applies. The description adds no parameter-level detail beyond the schema, which is acceptable given 100% coverage.

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?

Opens with a concrete verb and resource ("Create a link that lets one or more people join the flat") and immediately states why it exists — the share code alone does not permit joining. It is clearly distinguishable from invite_email and invites_list by naming both siblings.

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?

Gives an explicit when-to-use rule ("Use it when the user wants to hand the link over themselves") plus two named alternatives with the conditions that select them (email delivery, viewing existing links). It also states the permission model — "Any member may call it" — leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.