Move an email to the trash by default, or permanently remove it when permanent=True; deleting an item already in trash removes it permanently.
删除邮件。默认软删除=移入回收站；permanent=True 彻底删除（不可恢复，建议客户端配置人工确认）。 注意：删除已在回收站里的邮件会直接彻底删除。
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| permanent | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description carries the full burden and does well: it discloses that the default is destructive-but-reversible, that `permanent=True` is unrecoverable, and a non-obvious edge case (items already in the trash are hard-deleted regardless). It does not mention auth/permission requirements or rate limits, which is the remaining gap for a mutation tool with zero annotation coverage.
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 tight sentences plus a short caveat note. The default mode is front-loaded, the irreversible mode follows, and the edge case is separated out — no filler or repetition.
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 (2 params, one required), an output schema exists so return values need no explanation, and the description covers the destructive-mode semantics well. The only shortfall is the undocumented `id` parameter, which leaves a small hole in an otherwise complete definition.
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. It fully explains the `permanent` flag's semantics and default behavior, but says nothing about the required `id` parameter — an agent gets no confirmation that this is a message identifier rather than a folder or account id. Partial compensation only.
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 ('删除邮件') and immediately splits the operation into two modes: default soft delete (moves to trash) versus `permanent=True` hard delete. This distinguishes it adequately from siblings like `move_email` and `mark_email`, but it never explicitly names those siblings as alternatives, so the differentiation is implicit rather than stated.
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 gives clear conditions for choosing each mode: omit `permanent` for reversible removal, set `permanent=True` for irreversible deletion, and it explicitly recommends client-side manual confirmation before doing so. It also warns that deleting a message already in the trash bypasses soft delete entirely. What it lacks is any mention of sibling tools (e.g. using `move_email` when a plain trash move is intended).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.