Skip to main content
Glama
uk-kd

operbots-mcp

by uk-kd
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Список диалогов

dialogs_list
Read-onlyIdempotent

List and filter bot conversations by bot, chat type, mode, case, tag, or assigned operator. Find unread messages and dialogs handled by operators, including communities.

Instructions

Переписки ботов дела с отбором по боту, виду чата, режиму и подстроке. Показывает, где есть непрочитанное и какие диалоги ведёт оператор. Сообщества — группы и каналы, где состоит бот, — это те же диалоги с kind=community; в панели они в разделе «Сообщества».

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
botNoОтобрать по боту: название, @username или идентификатор.
tagNoОдна метка для отбора диалогов.
caseNoДело: название или идентификатор. Если не указать, берётся дело по умолчанию, иначе последнее открытое в панели.
kindNoВид чата: private — личная переписка, community — все сообщества, group — только группы, channel — только каналы. Без него — всё вместе.
modeNobot — ведёт сценарий; operator — перехвачен человеком.
limitNoСколько записей вернуть, максимум 200. По умолчанию 40.
queryNoПоиск по имени, нику и последнему сообщению.
offsetNoСколько записей пропустить.
assigned_toNoНазначены участнику: почта, имя или идентификатор из members_list.
only_unreadNoТолько с непрочитанными сообщениями.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.0
    • addedInput schema / properties / assigned_to
      Added value: +{
+  "description": "Назначены участнику: почта, имя или идентификатор из members_list.",
+  "type": "string"
+}
    • addedInput schema / properties / tag
      Added value: +{
+  "description": "Одна метка для отбора диалогов.",
+  "maxLength": 24,
+  "type": "string"
+}
  2. Changed1 schema field changedv0.1.17
    • addedInput schema / properties / kind
      Added value: +{
+  "description": "Вид чата: private — личная переписка, community — все сообщества, group — только группы, channel — только каналы. Без него — всё вместе.",
+  "enum": [
+    "private",
+    "community",
+    "group",
+    "channel"
+  ],
+  "type": "string"
+}
  3. First observedv0.1.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds real behavioral context beyond that: it discloses that results indicate unread presence and which dialogs are operator-handled. It does not mention pagination behavior or any rate/cost characteristics.

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?

Three sentences, front-loaded with purpose, then return-value hints, then the community mapping. Dense but no filler; each sentence adds something. Slightly more could be trimmed but nothing is wasted.

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 10-parameter, zero-required list tool with no output schema, the description supplies purpose, filtering intent, and the community/kind mapping. Return shape and pagination defaults are left to the schema (limit/offset described there), which is reasonable. No output schema means a small gap around result structure.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline is 3. The description goes one step beyond by reconciling a data-model subtlety the schema alone doesn't convey: communities (groups and channels the bot belongs to) are the same dialogs surfaced via kind=community, and are shown under 'Сообщества' in the panel.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb+resource+scope: listing a case's bot conversations with filters by bot, chat kind, mode and substring. An agent can tell this is the enumeration tool versus dialogs_get or dialogs_history. It stops short of naming a sibling it is not, which keeps it out of the top band.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the filtering vocabulary ('с отбором по боту, виду чата, режиму и подстроке') signals 'use me to browse/filter dialogs', but there is no explicit when-to-use or when-not versus dialogs_get, dialogs_history or counterparties_dialogs. No prerequisites or exclusions are offered.

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

Deploy Server

Other Tools