Invite a user to the API key's workspace as admin / editor / viewer (default editor). Admin role required to call. Sends a welcome email.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Optional display name; defaults to the email's local-part. | |
| role | No | Defaults to editor. Admins can't invite owners — that requires an existing owner. | |
| Yes | Invitee's email address. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds context beyond annotations by specifying the required admin role and the email side effect. There is no contradiction with annotations (idempotentHint=false, destructiveHint=false). However, it does not mention idempotency or destructibility.
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?
Two concise sentences with no wasted words. The first sentence covers purpose and roles; the second covers prerequisites and side effects. Front-loaded and efficient.
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?
For a simple invitation tool with few parameters and no output schema, the description is sufficiently complete. It covers purpose, roles, prerequisites, and side effects. Could optionally mention the return value, but not essential.
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?
All three parameters are already described in the schema (100% coverage). The description adds value by clarifying the default role ('default editor') and the default for the 'name' parameter ('defaults to the email's local-part').
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 clearly states the action ('Invite a user'), the target resource ('the API key's workspace'), and the allowed roles ('admin / editor / viewer'), distinguishing it from the sibling tool 'invite_reviewer' which likely invites external reviewers.
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?
The description explicitly states the prerequisite ('Admin role required to call') and the side effect ('Sends a welcome email'), but does not provide guidance on when not to use the tool or mention alternatives like 'invite_reviewer'.
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.
Each tool targets a distinct resource and action, with clear separation between CRUD operations, workflow management, and administrative tasks. No two tools appear to have overlapping purposes; even similar-sounding tools like list_change_requests and pinappai_list_apply_inbox serve different contexts.
The tool names consistently follow a verb_noun pattern, with a subset of workflow-related tools consistently prefixed with 'pinappai_'. There is no mixing of naming conventions, making the function of each tool predictable from its name.
With 38 tools, the server is significantly over the typical well-scoped range. While the tools cover many aspects of the platform, the sheer number makes it heavy for an agent to navigate effectively.
The server covers core operations for projects, workspaces, members, and API keys, but lacks programmatic creation, update, and individual deletion of change requests. This creates notable gaps in the ability to fully manage the CR lifecycle programmatically.
