Skip to main content
Glama

Shager

by ai.shager
OverviewDiscussionsAdmin

Invite someone to the team

invite_member
Destructive

Emails a person an invitation to join this organization's team as a viewer (read only), for every workspace (scope "all") or only some (workspace ids from list_workspaces). The invitation link works for 7 days; inviting an address that already has an open invitation updates and resends it. Sends email to a person, so it needs the publish scope and a key whose human manages the team. Agents can't invite editors or managers, so a misled agent can't hand someone write access: the human does that in the app (Team page). At most 30 invitation emails per organization per day. (Not available in an unclaimed sandbox.)

Input Schema

NameRequiredDescriptionDefault
roleNoviewer: read only. Editors and managers are invited by a person in the app.viewer
emailYes
scopeNo"all", or the workspace ids they may openall

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / role / default
      Added value: +"viewer"
    • changedInput schema / properties / role / description
      Previous value: -"editor: writes and schedules posts, answers comments. viewer: read only."New value: +"viewer: read only. Editors and managers are invited by a person in the app."
    • changedInput schema / properties / role / enum
      Previous value: -[
-  "editor",
-  "viewer"
-]New value: +[
+  "viewer"
+]
    • changedInput schema / required
      Previous value: -[
-  "email",
-  "role"
-]New value: +[
+  "email"
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations mark this as a non-readonly, non-idempotent, open-world mutation, and the description adds consequences the annotations cannot: the invite link expires in 7 days, re-inviting an existing open invitation updates and resends it, emails go out as a side effect, and there is a hard limit of 30 invitation emails per organization per day. It also discloses the security posture (viewer-only for agents), which is exactly the context an agent needs before writing.

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?

Every sentence carries real information and the primary action plus role constraint is front-loaded. It is a dense single paragraph with stacked parentheticals (sandbox note, list_workspaces pointer), which is slightly heavier to parse than necessary but not wasteful.

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 3-parameter email-sending mutation with no output schema, the description covers side effects, expiry, resend/update behavior, rate limits, required permissions, and unavailability conditions. An agent has everything it needs to decide whether and how to call it.

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 67% and the description fills the important remaining gap by explaining that scope is either 'all' or explicit workspace ids obtained from list_workspaces, and that role is constrained to viewer. It does not add format detail for email beyond the schema, but that parameter is already well constrained.

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?

States a specific verb and resource ('Emails a person an invitation to join this organization's team') and pins the effect down to a viewer role, all/partial workspace scope. It is clearly distinguishable from siblings like list_members and list_workspaces, which are read-only listing tools.

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?

It states when to use it (invite a viewer), where to get scope values ('workspace ids from list_workspaces'), and explicitly says what it cannot do (agents can't invite editors/managers; the human does that in the app's Team page). Prerequisites (publish scope, a key whose human manages the team) and exclusions (unclaimed sandbox) are spelled out.

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

All Shager 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