sota-agw-mcp

Gửi nháp (cần người xác nhận)

draft_send

DestructiveIdempotent

Sends an email draft via SMTP only after explicit client-dialog confirmation of recipients, content, and attachments; blocks sending when no confirmation dialog exists.

Instructions

Gửi nháp qua SMTP. LUÔN hỏi người dùng xác nhận qua hộp thoại của client (hiện đủ người nhận / nội dung / đính kèm). Client không có hộp thoại xác nhận → không gửi; hướng dẫn người dùng gửi bằng lệnh terminal.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "draft_id": "<draft_id>"
    },
    "name": "draft_send"
  }
}

Input Schema

Name	Required	Description	Default
`draft_id`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.11.0Nov 9, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive=true, openWorldHint=true, and readOnlyHint=false, so the safety profile is partly covered, but the description adds substantive behavior: actual SMTP transmission, a mandatory confirmation gate, and the no-dialog refusal path. It stops short of stating what happens to the draft after sending or how transport failures leave state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, with the action first and the confirmation constraint immediately after; every sentence carries an instruction the agent needs. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the destructive-send workflow with its confirmation requirement is well documented. Remaining gaps are minor: post-send draft state and error handling on SMTP failure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description never mentions draft_id, so it adds no meaning about which draft is sent, whether the ID comes from draft_create, or what happens if it is invalid. With one undocumented parameter the description should have compensated and did not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Gửi nháp qua SMTP' / send draft via SMTP) and even names the transport, so an agent knows exactly what the tool does. It does not distinguish itself from siblings such as draft_create, though the verb 'send' is distinctive enough that confusion is unlikely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit operating conditions: always obtain user confirmation through the client's dialog showing recipients/content/attachments, and if no dialog exists, do not send and instead instruct the user to use a terminal command. This is a clear precondition and a documented fallback, though it frames guidance around workflow rather than naming alternatives like draft_create.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server