Skip to main content
Glama
WACrew: WhatsApp AI automation

WACrew: WhatsApp AI automation

ler_mensagens

Reads one WhatsApp chat or group’s history—including text and existing transcripts—filtered by start date and capped by message limit for recent context.

Instructions

Lê o histórico de UM chat, grupo ou DM (texto + transcrições já feitas). Pra 'quem está esperando' em todos os chats use 'caixa_de_entrada'; o que chegou desde a última checagem nos chats com alerta, 'novidades'; um dia inteiro pra resumir, 'resumo_do_dia'; achar um termo, 'buscar'. Filtra por data inicial e limita a quantidade. Default: as 50 mais recentes (passe 'limite' maior, ou 'desde', pra ir além) — evita despejar o grupo inteiro quando você só quer o contexto recente. Cada msg traz timestamp (UTC) e hora_brt (hora de Brasília já convertida) — use a hora_brt pra falar de horário com o operador, NÃO leia o UTC como se fosse local. Mídia com texto junto traz esse texto em legenda (descreve a mídia), não em texto (que é msg de texto solta) — assim você sabe que a legenda se refere ÀQUELE vídeo/imagem, e não confunde com um texto enviado depois. Mensagens coladas do mesmo remetente (rajada: vídeo+texto+áudio numa tacada) compartilham um rajada (id) — trate-as como um bloco do mesmo assunto, não itens soltos.

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": {
      "grupo": "<grupo>"
    },
    "name": "ler_mensagens"
  }
}

Input Schema

NameRequiredDescriptionDefault
desdeNoISO date/datetime; só mensagens a partir daí
grupoYesslug do grupo (de listar_grupos) OU de uma DM: `dm-<55DDDnúmero>` (o número que você já tem, só dígitos) ou o jid. Telefone e LID da mesma pessoa são fundidos na leitura.
limiteNomáximo de mensagens (mais recentes); default 50 quando 'desde' também é ausente

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it states the default of 50 most recent messages and how to go beyond it, explains that timestamps are UTC while `hora_brt` is pre-converted Brasília time, clarifies `legenda` vs `texto`, and introduces the `rajada` grouping id. It does not discuss permissions, rate limits, or whether history is truncated server-side, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads purpose, then alternative routing, then default/limit behavior, then output-field semantics. Every sentence carries operational value — there is no filler, and the parenthetical explanations are parenthetical for good reason.

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 three-parameter read tool with no output schema, the description covers everything an agent needs: what is returned, the timestamp fields and their timezones, how media captions are represented, and how burst messages group. No return-shape ambiguity remains.

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 coverage is 100%, so both optional parameters are already documented in the schema. The description reinforces the default-50 behavior and says 'limite' higher or 'desde' to go further, but adds no format or syntax detail beyond what the schema states, so the baseline 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?

Opens with a specific verb and resource ('Lê o histórico de UM chat, grupo ou DM') and explicitly scopes it to a single conversation, plus notes that text and already-made transcriptions are returned. An agent can immediately distinguish this from the inbox/novidades/resumo_do_dia siblings.

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

Usage Guidelines5/5

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

Explicitly routes four alternative needs to their own tools: 'quem está esperando' → caixa_de_inbox, new items since last check → novidades, whole-day summary → resumo_do_dia, term search → buscar. It leaves no ambiguity about when this tool is the wrong choice.

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