Skip to main content
Glama
Sign In

MCP for Claude & ChatGPT

by com.tuqui
OverviewDiscussionsAdmin

Manage groups

tuqui_group
Destructive

Read the workspace's groups (named sets of people) and manage who is in them. action='list' returns every group; 'get' one with its members; 'save' creates a group when 'group' is absent and renames it when present (workspace admins only); 'delete' removes one (admins only); 'add' puts people in a group (with role='manager' they join as managers, admins only) and never changes the role of somebody already in it; 'set_role' names or un-names managers (admins only); 'remove' takes people out; 'leave' takes YOU out of a group, which anyone in it may do. A group's managers may add and remove its plain members, not other managers. Name the group with 'group' (its name or id) and the people with 'to' (email, name or user id). Only people who already accepted their invitation can be in a group.

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": {
      "action": "<action>"
    },
    "name": "tuqui_group"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoadd / remove / set_role: the people, by EMAIL, name or user id. A list.
nameNosave: the group's name. Required to create.
roleNoadd: the role of people who are NOT in the group yet, 'member' (default) or 'manager'. set_role: the new role, required. Managers are named by an admin.
groupNoThe group's name or id. Required for every action but 'list' and creating.
actionYesREQUIRED. What to do with the groups.
descriptionNosave: one line on who is in the group.
consent_tokenNoThe approval a person gave for THIS call in Tuqui. Bound to these arguments and valid once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare destructive/openWorld/readOnly; the description adds the real behavioral burden: per-action authorization, the manager-vs-member permission hierarchy, the rule that managers cannot add/remove other managers, and the prerequisite that only people who accepted an invitation can be in a group. Also flags that 'add' is idempotent w.r.t. existing members' roles.

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 a one-line purpose, then a dense but well-ordered action rundown ending with how to name the group and the people. Every clause carries information, though the single unbroken paragraph of semicolon-separated clauses is harder to scan than it needs to be.

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?

For a 7-parameter, no-output-schema tool with a nontrivial permission model, the description covers return shape implicitly ('list' returns every group, 'get' one with its members), authorization, and preconditions. The gap is consent_token: it is a required-in-practice approval bound to these arguments, and the description never explains when it is needed or how it is obtained.

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 baseline is 3, but the description adds genuine cross-parameter semantics the schema only states mechanically: 'save' creates when 'group' is absent and renames when present, and role='manager' applies only to people not yet in the group. It does not mention consent_token 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?

Opens with a specific verb+resource ('Read the workspace's groups ... and manage who is in them') and then enumerates all eight actions with what each does, so the agent knows the tool's full surface before opening the schema. It is clearly distinct from the sibling tuqui_member (people) by being about named sets of people.

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?

Every action is scoped with when to use it and who may use it ('workspace admins only', 'admins only', 'anyone in it may do'). It also implies the alternatives: 'add' is stated to never change an existing member's role, which routes the agent to 'set_role', and 'leave' is distinguished from 'remove' as taking YOU out.

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

All MCP for Claude & ChatGPT toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources