Skip to main content
Glama

Find conversations waiting for a reply

list_unanswered_conversations
Read-only

Conversations waiting for a reply, newest first, at most 50.

With waiting_on: "user" (the default), who is waiting for the user's reply: the one-to-one conversations where the other person wrote last, and the groups where someone mentioned the user or replied to one of their messages, in the last 30 days, and the user has not written since. With waiting_on: "contact", who still owes the user a reply: the conversations, groups included, whose last message is the user's. Each carries the same summary as search_conversations, is_group, and last_message, the message waiting for the reply.

last_message.seen says whether the one it was sent to has opened the chat since it arrived: the user on any of their devices, or the other person, as WhatsApp's blue ticks show; in a group waiting on the others, whether at least one of them has, which is less than WhatsApp's blue ticks, shown only once everyone has read. False means not read yet. Null means Werify has never seen such a read in this chat, which says nothing either way; someone who turned read receipts off never sends one.

Conversations shared with the user are left out. A call, a reaction, a system notice or a deleted message does not count as writing, so the message before it decides. Werify only knows what it captured: a message sent after a conversation stopped being captured, or after a WhatsApp export was imported, is missing here, so check last_message's date. Pass an id to get_conversation to read the conversation before answering.

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_unanswered_conversations"
  }
}

Input Schema

NameRequiredDescriptionDefault
waiting_onNoOptional: "user" for the conversations waiting for the user's reply (the default), "contact" for the ones where nobody has replied to the user yet.

Output Schema

NameRequiredDescriptionDefault
next_stepNoPresent only when capture is paused for billing on one of the user's numbers, so a message waiting for a reply may not have arrived. Relay it to the user.
conversationsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already cover read-only, non-destructive, closed-world, but the description goes well beyond them: the 50-item cap, the 30-day lookback, exclusions for shared conversations, and the rule that calls/reactions/system notices/deleted messages don't count as writing. The capture-completeness caveat ('a message sent after a conversation stopped being captured ... is missing here') is exactly the kind of limitation an agent cannot infer elsewhere.

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-loaded with the core fact, then layered detail; nearly every sentence earns its place. Some passages are heavy going, particularly the seen/null explanation and the trailing 'Werify only knows what it captured' paragraph, which could be tightened without losing information.

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 single optional-parameter read tool with a declared output schema and safety annotations, this is complete: eligibility rules, exclusions, staleness caveats, and semantics of the returned last_message.seen flag are all covered. Nothing an agent needs in order to call or interpret it 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% and the single parameter is documented, so the baseline is 3; the description adds real meaning the schema lacks — that 'user' is the default, that the 30-day window applies only to the user mode, and how each mode treats groups.

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 the resource precisely ('conversations waiting for a reply') plus ordering and a hard cap ('newest first, at most 50'), and immediately splits the two populations via the waiting_on values. An agent can distinguish this from search_conversations without opening the 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 explicit conditions selecting each mode: 'user' for one-to-one or mention/reply threads within 30 days, 'contact' for conversations whose last message is the user's. It also routes to get_conversation for follow-up reading. It stops short of an explicit 'use search_conversations instead when X' exclusion, so a 4 rather than 5.

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