Skip to main content
Glama
Sign In

DOS AI

by pro.dosai
OverviewDiscussionsAdmin

List old WhatsApp chats from the owner's phone

dosai_list_old_chats
Read-onlyIdempotent

WhatsApp chats the owner had in the phone BEFORE the number was connected, newest first: phone (null when WhatsApp hides it), name (set by the person), saved_name (the owner's contacts), had_messages (there was a real conversation, not just an empty chat entry), saved_in_contacts, last_message_at and last_client_message_at (null = unknown: times are kept only for chats seen since 05.11.2026), conversation_id (the dialog in the cabinet, null = none yet). The messages themselves are not here: open the dialog with dosai_open_conversation and the old messages are pulled from the phone with the first new message. Private chats of the owner are in this list too (family, friends): do not write to someone just because they are here. Requires editor role.

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": {
      "project_id": "<project_id>"
    },
    "name": "dosai_list_old_chats"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, default 1.
limitNoRows per page, default 100, at most 200.
project_idYesProject id, as returned by dosai_list_projects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, open-world and non-destructive, so the safety profile is covered. The description adds real context beyond that: null semantics for phone and timestamps, the caveat that time data exists only for chats seen after 05.11.2026, the editor-role requirement, and the warning that the owner's private chats appear in the results. Pagination behavior and typical result volume are not discussed.

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?

The key concept and its 'BEFORE connection' scoping are front-loaded, and the long parenthetical field glossary is load-bearing in the absence of an output schema. It is dense and runs long as a single sentence chain, but no sentence is filler.

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?

With no output schema, the description compensates by enumerating every returned field with null semantics and the timestamp-retention caveat, and it states the permission requirement and the privacy risk. An agent has enough to call it correctly and interpret the rows without further documentation.

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 description coverage is 100%: project_id, page and limit are all documented in the schema. The description adds nothing about these parameters (no guidance on paging depth or limits), 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?

The description opens with a precise verb+resource+scope: WhatsApp chats that existed on the phone BEFORE the number was connected, returned newest first. It is clearly separable from dosai_list_conversations and dosai_open_conversation, which cover the live dialog rather than pre-connection history.

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?

It routes the agent elsewhere for the actual content ('The messages themselves are not here: open the dialog with dosai_open_conversation') and adds an explicit behavioral caution ('do not write to someone just because they are here'), plus the editor-role prerequisite. It never explicitly says when this list is the wrong choice versus dosai_list_conversations, so it falls just short of a full when/when-not statement.

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

All DOS AI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources