Skip to main content
Glama
FengSui 4G/5G Router MCP Server

FengSui 4G/5G Router MCP Server

Delete SMS From the Router

delete_sms
DestructiveIdempotent

Delete specific router SMS messages by UID, with required confirmation and optional unread handling; deleted items go to Recently deleted or are removed permanently when trash days are zero.

Instructions

Delete specific messages (uids from get_sms_thread) from the router. FengSui keeps them in Recently deleted for the days the owner chose (trashDays in the result; 0 means deleted for good), where only the owner can restore them or delete them for good. Requires confirm: true, at most 20 per call, and refuses unread messages unless includeUnread is true.

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": {
      "uids": "<uids>",
      "confirm": "<confirm>"
    },
    "name": "delete_sms"
  }
}

Input Schema

NameRequiredDescriptionDefault
uidsYesThe messages to delete, by the uid get_sms_thread gives each; at most 20.
confirmYesMust be true: the user explicitly asked for this change.
includeUnreadNoAllow deleting unread messages (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.9.5

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real behavioral context beyond them: deletion is recoverable via a Recently-deleted area for trashDays (0 = permanent), only the owner can restore or purge, the batch cap is 20, and unread messages are protected by default. That is exactly the consequence-level detail an agent needs before a destructive call.

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

Conciseness5/5

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

Three tight sentences, front-loaded with what is deleted and where the uids come from, followed by retention, then constraints. No filler or repetition across sentences.

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

Completeness5/5

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

For a destructive three-parameter tool with no output schema and full annotation coverage, the description supplies everything needed to call it safely: identifier source, batch limit, confirmation requirement, unread guard, and the shape of the post-delete state. Nothing material is missing.

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

Parameters3/5

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

All three parameters are fully described in the schema (100% coverage), and the description largely restates them – confirm: true, the 20-item cap, includeUnread gating. The only added meaning is the mention that trashDays appears in the result, which is about the response rather than the inputs, so the baseline 3 applies.

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

Purpose5/5

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

States a specific verb and resource ('Delete specific messages ... from the router') and pins the identifier source by naming the sibling that produces the uids (get_sms_thread). An agent can distinguish this from mark_sms_read, preview_sms, or list_sms_threads without opening a schema.

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?

Gives concrete invocation conditions: confirm must be true, max 20 uids per call, and unread messages are refused unless includeUnread is set. It stops short of naming an explicit alternative or a 'do not use when' case, so it is strong context rather than full routing guidance.

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