Delete an iCloud Mail mailbox or folder only after it is empty; optionally preview the removal with a dry run.
Delete a mailbox/folder. The folder must be empty first.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Mailbox path to delete | |
| dryRun | No | If true, report exactly what would change and do not modify anything |
Changes observed during successful MCP inspections.
v2.8.0Input schema / properties / dryRunAdded value: +{
+ "description": "If true, report exactly what would change and do not modify anything",
+ "type": "boolean"
+}v2.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden. It discloses the critical empty-folder precondition, which is real added value, but says nothing about permanence/reversibility, what happens to subfolders, or whether the operation can be undone — gaps that matter for a destructive tool.
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 short sentences, the action first and the precondition second; nothing is wasted and nothing needs to be read twice.
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 two-parameter tool with full schema coverage and a dryRun escape hatch, the description covers the essential constraint. Remaining gaps (permanence, subfolder handling) are modest given there is no output schema and the schema itself documents the safety valve.
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 coverage is 100%, with both 'name' and 'dryRun' documented in the schema itself. The description adds no meaning beyond that (e.g., path format, anchoring, or dryRun behavior), so the baseline 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?
States a specific verb and resource ('Delete a mailbox/folder'), which is unambiguous and distinct from sibling tools like delete_email, delete_calendar, and delete_reminder. It does not, however, explicitly contrast itself with adjacent siblings such as create_mailbox, rename_mailbox, or empty_trash.
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 folder must be empty first' is a genuine precondition that tells the agent when this call will fail, which is more than most terse definitions offer. But there is no guidance on alternatives (e.g., using delete_email or bulk_delete to clear contents, or empty_trash) and no statement of when to prefer this over those paths.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.