Skip to main content
Glama

List connected WhatsApp numbers

list_connected_numbers
Read-onlyIdempotent

List the WhatsApp numbers connected to the user's Werify account, with each one's status. Use it after connect_whatsapp_number to confirm the pairing landed (linking → syncing → ready), and before telling the user what a number can do. A number is keyed by its phone; a linking entry with no phone is a pairing still waiting for its code. With no number at all, the result carries a next_step on how to connect one: offer it to the user.

A pairing can also end at sync_stalled instead of ready: WhatsApp sent no history at all and will not. That one does not resolve by waiting or by polling this tool, so stop doing both and tell the user what stall_remedy says.

ready means the initial sync finished and the number can capture conversations through start_live_capture when capture_funded is true. A positive wallet balance is enough, or the user can enable auto-topup with a card in Werify. A suspended number cannot capture: follow its funding_note, even if the account-level capture_funded is true. A positive remaining balance does not mean a suspension was lifted. A new account starts with free capture: its first chats on one number capture at no charge, for a limited time. Every other capture, and every capture once free capture ends, is paid from the account's balance or by that number's subscription. list_connected_numbers says what funds each number, and what to tell the user, in its funding_note.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_connected_numbers"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
numbersNo
next_stepNoPresent only when no number is connected: how to connect one, to offer the user.
funding_hintNoPresent only when capture_funded is false: what the user must do, and where.
capture_fundedNoWhether the user's wallet can fund capture on any number (positive balance, or auto-topup on with a card), or a free capture is still unused. On an account without a wallet, whether some number can capture or a free capture is still unused. A number may also be funded on its own — see each number's capture_funded. Connecting a number never needs funding; capturing does. This does not lift an individual number's billing suspension: check its status and funding_note.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description instead spends its words on the state machine (`linking` → `syncing` → `ready`, plus terminal `sync_stalled`), funding preconditions for `start_live_capture`, and the fact that `suspended` overrides a positive balance and an account-level `capture_funded`. That is behavior an agent could not recover from the annotations or the zero-parameter schema.

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

Conciseness3/5

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

Purpose and workflow are correctly front-loaded, but the body runs to four paragraphs and drifts well past what is needed to select or call a zero-parameter list tool. Passages on wallet balance, auto-topup, subscription billing, and free-capture windows describe downstream capture economics, and the closing sentence restates that this information lives in `funding_note` — content that is redundant once the tool documents the field.

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 read-only, zero-parameter lister with an output schema, the definition supplies everything an agent needs to act on the response: state transitions, the terminal stall case with a pointer to `stall_remedy`, the suspension override, and the empty-account next step. Nothing material is left for the agent to guess.

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

Parameters5/5

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

The tool takes no input parameters, so there is nothing for the description to disambiguate; baseline for a zero-param tool is 4, and the description adds relevant framing about what the keyed results represent (a number keyed by phone, a `linking` entry with no phone being a pairing awaiting its code).

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?

Opens with a specific verb+resource+scope: "List the WhatsApp numbers connected to the user's Werify account, with each one's status." It is immediately distinguishable from the sibling `connect_whatsapp_number`, which it names as the preceding step rather than a substitute.

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

Usage Guidelines5/5

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

Gives explicit placement in a workflow ("Use it after `connect_whatsapp_number`... and before telling the user what a number can do") and an explicit when-not: in the `sync_stalled` state it says not to poll this tool and why. It also prescribes an action for the empty-result case (offer `next_step` to the user), leaving nothing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources