Skip to main content
Glama

kommo_talks_messages

Read-onlyIdempotent

Mensagens (texto) das conversas do Kommo: WhatsApp, Instagram, Telegram etc. Informe talk_id/talk_ids, ou lead_id/contact_id para ler todas as conversas daquele lead/contato. Devolve, por mensagem, autor (client = cliente, user = usuário da conta, bot), texto, tipo (text/picture/video/voice/audio/file/sticker/location/contact), anexo e created_at. Paginação por page/limit (por conversa) e filtro por date_from/date_to. Só leitura. Exige o escopo "External chat history" no token da conta.

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": "kommo_talks_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
limitNo
accountNo
date_toNo
lead_idNo
talk_idNo
talk_idsNo
date_fromNo
contact_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, but the description adds material context beyond them: the mandatory 'External chat history' token scope, the per-message return shape (author roles client/user/bot, type values, attachment, created_at), and the fact that pagination is applied per conversation rather than globally. Missing only failure behavior and default page size.

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?

A single dense paragraph with the resource and channel scope front-loaded, followed by identifier modes, then return shape, then pagination and auth. Every sentence carries information; the long enumeration of message types is justified because it tells the agent exactly what the 'tipo' field can contain.

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?

With 9 undocumented parameters, no output schema, and 0% schema coverage, the description had to supply both parameter meaning and return-value detail, and it largely does. The gaps (account param, default limit, precedence between talk_id and lead_id) are secondary but real.

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 coverage is 0%, so the description carries the full burden and does most of it: it explains the alternative identifier modes (talk_id/talk_ids vs lead_id/contact_id), that page/limit paginate per conversation, and that date_from/date_to filter. The 'account' parameter and accepted date formats are left undocumented, which keeps it from a 5.

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 combination: reads text messages from Kommo conversations (WhatsApp, Instagram, Telegram), and enumerates the returned fields, so an agent knows exactly what comes back. It does not explicitly differentiate itself from kommo_talks_get or kommo_talks_list, which likely overlap in domain, so it stops short of a 5.

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?

The description tells the caller which identifiers to supply (talk_id/talk_ids, or lead_id/contact_id to read all conversations of a lead/contact), which is usage guidance in the input sense. It never says when NOT to use it or names an alternative sibling for a narrower/broader read, so guidance is implied rather than explicit.

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.