contract-testing_admin_invite_usersSend invitations to new users in the SmartBear contract-testing admin tool by providing their names and email addresses.
Send invitations to new users (admin).
Toolset: Admin
Parameters:
users (array) required: List of users to invite
| Name | Required | Description | Default |
|---|---|---|---|
| users | Yes | List of users to invite |
| Name | Required | Description | Default |
|---|---|---|---|
| users | No | ||
| _links | No |
Changes observed during successful MCP inspections.
v0.43.0Output schema / (root)Previous value: -nullNew value: +{
+ "$defs": {
+ "EmbeddedLink": {
+ "additionalProperties": {},
+ "properties": {
+ "href": {
+ "type": "string"
+ },
+ "name": {
+ "type": "string"
+ },
+ "templated": {
+ "type": "boolean"
+ },
+ "title": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "Permission": {
+ "additionalProperties": {},
+ "properties": {
+ "description": {
+ "type": "string"
+ },
+ "group": {
+ "type": "string"
+ },
+ "label": {
+ "type": "string"
+ },
+ "scope": {
+ "type": "string"
+ },
+ "uuid": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "User": {
+ "additionalProperties": {},
+ "properties": {
+ "_embedded": {
+ "additionalProperties": {},
+ "properties": {
+ "roles": {
+ "items": {
+ "$ref": "#/$defs/UserRole"
+ },
+ "type": "array"
+ },
+ "teams": {
+ "items": {
+ "$ref": "#/$defs/UserTeam"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "_links": {
+ "additionalProperties": {},
+ "properties": {
+ "pf:tokens": {
+ "$ref": "#/$defs/EmbeddedLink"
+ },
+ "self": {
+ "$ref": "#/$defs/EmbeddedLink"
+ }
+ },
+ "type": "object"
+ },
+ "active": {
+ "type": "boolean"
+ },
+ "authenticationSource": {
+ "type": "string"
+ },
+ "createdAt": {
+ "type": "string"
+ },
+ "email": {
+ "type": "string"
+ },
+ "externalId": {
+ "type": "string"
+ },
+ "externalIdpId": {
+ "type": "string"
+ },
+ "externalIdpUsername": {
+ "type": "string"
+ },
+ "firstName": {
+ "type": "string"
+ },
+ "identityProviderId": {
+ "type": "string"
+ },
+ "lastLogin": {
+ "type": "string"
+ },
+ "lastName": {
+ "type": "string"
+ },
+ "lastTimeTokenAccessed": {
+ "type": "string"
+ },
+ "name": {
+ "type": "string"
+ },
+ "seatType": {
+ "type": "string"
+ },
+ "type": {
+ "anyOf": [
+ {
+ "const": 0,
+ "type": "number"
+ },
+ {
+ "const": 1,
+ "type": "number"
+ }
+ ]
+ },
+ "typeDescription": {
+ "type": "string"
+ },
+ "updatedAt": {
+ "type": "string"
+ },
+ "uuid": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "UserRole": {
+ "additionalProperties": {},
+ "properties": {
+ "_links": {
+ "additionalProperties": {},
+ "properties": {
+ "self": {
+ "$ref": "#/$defs/EmbeddedLink"
+ }
+ },
+ "type": "object"
+ },
+ "name": {
+ "type": "string"
+ },
+ "permissions": {
+ "items": {
+ "$ref": "#/$defs/Permission"
+ },
+ "type": "array"
+ },
+ "uuid": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "UserTeam": {
+ "additionalProperties": {},
+ "properties": {
+ "_links": {
+ "additionalProperties": {},
+ "properties": {
+ "pf:integrations": {
+ "$ref": "#/$defs/EmbeddedLink"
+ },
+ "pf:membership": {
+ "$ref": "#/$defs/EmbeddedLink"
+ },
+ "self": {
+ "$ref": "#/$defs/EmbeddedLink"
+ }
+ },
+ "type": "object"
+ },
+ "name": {
+ "type": "string"
+ },
+ "uuid": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ }
+ },
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": {},
+ "properties": {
+ "_links": {
+ "additionalProperties": {},
+ "properties": {
+ "self": {
+ "$ref": "#/$defs/EmbeddedLink"
+ }
+ },
+ "type": "object"
+ },
+ "users": {
+ "items": {
+ "$ref": "#/$defs/User"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+}v0.40.0v0.34.0v0.27.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true. The description adds nothing beyond that: it never says an email is dispatched, whether users are created in a pending state, or what happens when an invitation is re-sent to an already invited user (a real risk given idempotentHint=false).
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 definition is short and front-loaded with the action, but the 'Parameters' block largely duplicates information already present in the input schema, which is wasted space for a one-parameter tool.
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?
With an output schema present and full parameter coverage, the structured data carries most of the load. What remains missing is behavioral context specific to an invitation flow (delivery mechanism, duplicate handling, permission requirements), which an agent would want before invoking a non-idempotent, open-world write.
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 100% and there is a single required parameter, so the schema already documents the shape of 'users' including the nested name/email fields. The description merely restates 'List of users to invite' without adding constraints such as email format or duplicate handling, so the baseline of 3 applies.
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 states a specific verb and resource ('Send invitations to new users'), which clearly distinguishes this tool from read-style siblings like contract-testing_admin_list_users. It does not, however, differentiate itself from the closely related contract-testing_admin_create_user, leaving the invite-vs-create distinction to inference.
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?
There is no when-to-use guidance, no prerequisites (such as required admin permissions or whether invited users must not already exist), and no mention of the sibling alternatives. The only contextual hint is the '(admin)' marker and the 'Toolset: Admin' line.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.