sota-agw-mcp

Kiểm tra luật cho email dán vào

email_check

Read-only

Checks pasted email content against G01 advertising and G02 security rules, flagging Reply-To domain mismatches, account changes, and spoofed domains for quick triage.

Instructions

Chạy luật G01 (quảng cáo) + G02 (an ninh: Reply-To khác domain, đổi tài khoản, domain giả…) cho email người dùng dán vào hội thoại.

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": {
      "sender": "<sender>",
      "subject": "<subject>",
      "body": "<body>"
    },
    "name": "email_check"
  }
}

Input Schema

Name	Required	Description	Default
`body`	Yes
`sender`	Yes
`subject`	Yes
`reply_to`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.11.0Nov 9, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already establish this is a read-only, closed-world operation, so the safety profile is covered. The description usefully adds that it applies two named rule sets and lists concrete G02 triggers (Reply-To domain mismatch, account change, lookalike domain), which is real behavioral detail beyond the annotations. It stops short of saying whether all rules always run or how findings are reported per rule.

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?

A single front-loaded sentence: the action comes first, then the rule elaboration. Nothing is redundant, though the parenthetical list of checks sprawls slightly and could be tightened.

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

Completeness3/5

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. However, with four undocumented parameters and low schema coverage, the definition leaves the agent guessing about field mapping, especially the optional reply_to, which is precisely the field the G02 checks hinge on.

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% across four parameters (sender, subject, body, reply_to), so the schema provides no semantics at all and the description must compensate. It only gestures at 'the email the user pasted' and never explains which parts map to which field or what the optional reply_to is for, leaving three required fields undifferentiated.

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?

Names a specific action (run rules G01 and G02) on a specific resource (an email the user pasted into the conversation), and the parenthetical enumerates the security checks, making it distinguishable from siblings like mail_read or mail_list_recent, which operate on the mailbox rather than pasted text. Clear, though it never says what the result looks like.

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

Usage Guidelines3/5

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

The phrase 'email người dùng dán vào hội thoại' implies the usage context (pasted email content, not a stored message), which is enough to route an agent away from the mailbox-reading siblings. It does not state exclusions or name alternatives explicitly, so guidance remains implied rather than directive.

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

Deploy Server