Skip to main content
Glama

Remove people from a Role

remove_role_members
DestructiveIdempotent

Remove people from one Role. user_ids are the ids list_users reports. Each id is reported as removed, not_member, refused, or outcome_unknown with a code. Everyone keeps Member. Removing Member is always refused with member_role_required. Change at most 25 people's tiers per call. For outcome_unknown, repeat the same edit as the per-person message explains.

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": {
      "role_id": "<role_id>",
      "user_ids": "<user_ids>"
    },
    "name": "remove_role_members"
  }
}

Input Schema

NameRequiredDescriptionDefault
role_idYesUUID of the Role
user_idsYesThe ids list_users reports, for members and invitations

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations (destructive, idempotent, not read-only) by disclosing the per-id outcome vocabulary — removed, not_member, refused, outcome_unknown with a code — plus the Member invariant and its member_role_required error. The retry instruction for outcome_unknown is exactly the kind of partial-failure behavior an agent cannot infer from structured fields.

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 the action, then the id source, then the outcome model, then constraints — a sensible information order with no filler. The phrase 'Change at most 25 people's tiers per call' is slightly confusing since this tool removes role membership rather than changing tiers.

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?

With no output schema, the description usefully carries the return-value burden by enumerating per-id outcomes and the retry path, which is what an agent needs for a destructive bulk operation. It does not say whether the call is atomic, what happens if more than 25 ids are supplied, or how refused vs not_member differ in effect.

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%, and the description's note that user_ids are 'the ids list_users reports' largely restates the schema's own parameter description. It adds no format, batching, or validation detail for role_id beyond the schema's UUID note, so the baseline of 3 applies.

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?

States a specific verb and resource with scope: 'Remove people from one Role.' An agent can immediately tell this is a membership-removal mutation scoped to a single role, and the sibling name add_role_members makes the inverse obvious. It stops short of naming an alternative tool for the multi-role or single-user cases, so it is clear but not explicitly differentiated.

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 concrete operating context: user_ids come from list_users, at most 25 people per call, Member cannot be removed, and outcome_unknown should be retried with the same edit. That covers how to use it and one hard limit, but there is no explicit statement of when to prefer a different tool (e.g., remove_user for a single user).

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