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

FengSui 4G/5G Router MCP Server

Add or Rename a Contact

upsert_contact
Idempotent

Add or rename a contact for a phone number in the local encrypted contact book; explicit confirmation is required, and adding does not authorize SMS recipients.

Instructions

Add a contact or rename the contact that owns this number in the local encrypted contact book. A number you add here does not become an allowed send_sms recipient until the user saves it themselves. Requires confirm: 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": {
      "phone": "<phone>",
      "name": "<name>",
      "confirm": "<confirm>"
    },
    "name": "upsert_contact"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe name to show for this number.
noteNoAn optional note kept with the contact.
phoneYesThe contact's number, international (+353…) or national.
confirmYesMust be true: the user explicitly asked for this change.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.9.5

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly=false, idempotent=true and destructive=false, and the description is consistent with all three. It adds real behavioral context beyond them: the store is a local encrypted contact book, the write does not grant send_sms eligibility until the user saves it, and the call is gated on confirm being true with explicit user intent. It doesn't disclose what happens when confirm is false or how a rename collides with an existing contact, which keeps it below a 5.

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?

Two sentences, zero filler, and the most decision-relevant fact (this does not make the number a send_sms recipient) is front-loaded right after the purpose. The confirm requirement is appended last where it belongs as a precondition.

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?

With no output schema, four fully-described parameters, and annotations covering the safety profile, the description supplies what an agent needs to invoke it correctly: purpose, scope of effect, and the confirm gate. The remaining gap is error/edge behavior, such as a failed confirm or a name collision on rename, which an agent would have to discover at call time.

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?

Schema coverage is 100%, so all four parameters are already documented, setting the baseline at 3. The description adds one genuinely useful piece of semantics beyond the schema: the phone number is the identity key, so passing an existing number renames rather than duplicates. The note about confirm merely restates the schema's own wording, so the net gain is modest.

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?

The description names a concrete verb pair and resource: add a contact or rename the contact that owns this number in the local encrypted contact book. It also implicitly distinguishes itself from search_contacts by scoping the operation to writes in the local contact book, and it draws a bright line against the send_sms siblings by stating the number does not become an allowed recipient.

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?

Usage context is clear: this is the tool for creating or renaming a contact entry, and the agent is told the practical consequence (no SMS permission is granted) plus the hard prerequisite that confirm must be true with explicit user intent. What's missing is an explicit alternative or exclusion, such as pointing to search_contacts for lookups or stating what to do when the user has not asked for the change.

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