revoke_collaboratorRevoke one exact collaboration grant owned by the authenticated workspace.
| Name | Required | Description | Default |
|---|---|---|---|
| grantId | Yes | ||
| idempotencyKey | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| grantId | Yes | ||
| revoked | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "grantId": {
+ "format": "uuid",
+ "type": "string"
+ },
+ "revoked": {
+ "const": true,
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "revoked",
+ "grantId"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, so the description does not need to restate them. It adds useful scope ('one exact grant owned by the authenticated workspace'), but it does not discuss consequences such as irreversibility or effects on the collaborator's access beyond revocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single front-loaded sentence with no filler, placing the verb and core resource first. Every phrase ('one exact', 'owned by the authenticated workspace') earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple, has annotations covering destructive and idempotent behavior, and has an output schema, so the description can stay short. However, it leaves an agent without an explicit differentiator from revoke_collaboration_invitation and does not clarify the semantics of idempotencyKey, making it only minimally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, but it only hints at grantId via 'one exact collaboration grant' and says nothing about idempotencyKey, its format, or its role. The schema's field names and types are the only real semantic source, which is insufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Revoke') and resource ('collaboration grant') and adds the scope 'owned by the authenticated workspace.' This clearly distinguishes the action from related sibling tools such as revoke_collaboration_invitation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It implies the tool is for an existing, exact collaboration grant rather than a pending invitation, but it never explicitly states when to prefer this tool over revoke_collaboration_invitation or other alternatives. The context is present only by inference from the wording.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target a distinct resource and action, and lifecycle pairs like publish_note_listing vs publish_media_listing or get_note vs get_collaboration_note are separated by clear wording. A few near-pairs such as move_file vs move_workspace_item and trash_file vs trash_workspace_item could still cause an agent to pick the wrong tool without careful reading.
All 38 tools follow one consistent verb_noun snake_case pattern with no camelCase or mixed conventions. Even less common verbs like upsert, trash, purge, and validate are applied uniformly, making the tool set predictable.
38 tools is well above the 25+ threshold and makes the overall surface feel heavy for tool selection. The number is defensible given the broad workspace, collaboration, and marketplace scope, but as a single MCP server it is not especially well-scoped.
The tool set covers workspace content lifecycle, collaboration, public pages, marketplace listings, Stripe seller flow, and agent registration without major dead ends. Minor gaps exist, such as no permanent delete outside of the trash flow and no direct collaboration-note deletion, but core workflows are supported.