Skip to main content
Glama

List capturable chats

list_capturable_chats
Read-onlyIdempotent

List the chats a connected WhatsApp number can capture — the phone's own conversation list, newest activity first. Every chat carries a chat_id, which the capture tools take; a 1:1 is also named by contact_phone and a group by name, the way the user names them. chat_jid is deprecated. When Werify already captures a chat, the row also carries the conversation_id the read tools use and whether the capture is running or stopped. Filter by name with query, by recent activity with active_since and by kind; total counts what the filters kept, and large lists page with cursor. Pass the phone from list_connected_numbers, or omit it when the user has a single connected number.

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_capturable_chats"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoOptional: "direct" for one-to-one chats only, "group" for groups only. Omit for both.
phoneNoThe connected number, as returned by list_connected_numbers. Omit it when the user has a single connected number; with more than one, the call is refused listing them.
queryNoOptional substring to match against chat names (case- and accent-insensitive).
cursorNoThe next_cursor from a previous page; carries the phone and every filter with it.
active_sinceNoOptional YYYY-MM-DD, a day on the phone's calendar: only chats with a message on or after it. Chats whose last activity the phone never reported are left out, and last_message_at comes back in UTC, so it can read as the neighbouring day. With kind, this is how to count the chats of a period from total instead of paging the whole list.

Output Schema

NameRequiredDescriptionDefault
chatsNo
totalNoHow many chats match (before paging).
next_cursorNoPass back as cursor to get the next page; null on the last page.
estimates_usedNoHow many distinct-chat estimate slots are occupied on this number.
estimates_remainingNoRemaining onboarding allowance; null when estimates are not limited.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive safety, so the description's job is to add behavior — and it does: ordering (newest activity first), the `chat_jid` deprecation, that rows gain `conversation_id` and capture running/stopped status when Werify already captures the chat, and the multi-number refusal behavior. It doesn't cover pagination limits or response shape, but an output schema exists and the annotations carry the safety profile.

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?

Front-loads what the tool returns and the identifier fields an agent needs before the filters, and every sentence carries information. It is somewhat dense — the `chat_jid` deprecation and the UTC/last_message_at caveat add length — but nothing is redundant with the schema or annotations.

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?

For a 5-param read tool with an output schema and full annotation coverage, the description covers ordering, identifiers, filter combination, pagination, and the multi-number failure mode. The main remaining gap is explicit guidance on when to use this versus search_conversations/list_connected_numbers, but nothing an agent needs to call it correctly is missing.

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?

Schema coverage is 100%, so the baseline would be 3, but the description adds real meaning beyond the schema: it ties `phone` to `list_connected_numbers` and the multi-number refusal, frames `active_since` as a way to count a period via `total` rather than page through everything, and notes `cursor` carries the phone and filters with it. These are cross-field/task-level semantics the schema fields don't supply.

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 plus scope: 'List the chats a connected WhatsApp number can capture — the phone's own conversation list, newest activity first.' It distinguishes that this is the phone's own list rather than Werify's stored conversations, and names the fields identifying each chat. An agent can separate this from list_connected_numbers or search_conversations 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 practical routing: pass `phone` from `list_connected_numbers` or omit it when there is a single number, and explains that with multiple numbers the call is refused. It also explains how to count a period's chats from `total` with `kind` + `active_since` instead of paging. It stops short of explicitly saying when not to use it (e.g. versus search_conversations for existing captured chats), so this is clear context without explicit exclusions.

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