Create a new email mailbox on an ISPConfig server for a specific client by providing client ID and mailbox parameters such as server ID, email, password, name, and quota.
Create a new mailbox
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes | Mailbox params (server_id, email, password, name, quota, etc.) | |
| client_id | Yes | Client ID |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Create a new mailbox' and does not reveal whether duplicate email addresses are rejected, what permissions or preconditions are required, whether the action is reversible, or what the response contains. For a mutating operation with zero annotation coverage, this is a significant gap.
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 wasted words. It is concise and immediately understood. However, it is so minimal that it reads more like a label than a complete tool definition, so it loses a point on structure despite being 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?
The tool has nested parameters, no output schema, and no annotations, so the description needs to compensate with context. It does not cover preconditions (e.g., existing client and mail domain), required vs optional mailbox fields, duplicate handling, or response behavior. An agent calling this tool would have to infer most operational context from the schema and sibling tool names.
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?
The input schema describes both parameters, with client_id labeled 'Client ID' and params labeled 'Mailbox params (server_id, email, password, name, quota, etc.)'. Because schema description coverage is 100%, the description does not need to add much; it correctly identifies the resource and provides example param names inside the schema itself. The tool description itself adds no extra parameter detail, so a baseline score of 3 is appropriate.
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 ('Create') and resource ('mailbox'), making the operation immediately clear. It distinguishes from siblings like mail_user_update, mail_user_delete, mail_domain_add, mail_alias_add, and mail_forward_add by targeting the mailbox resource and the add action. It does not explicitly contrast with these siblings, but the resource naming is sufficient for basic identification.
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 gives no guidance on when to use this tool versus alternatives. It does not mention that a mail domain must already exist, that client_id must reference a valid client, or that mail_user_get/update/delete cover related lifecycle operations. Usage context is only implied by the tool name and generic 'create' wording.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.