WACrew

revisar_texto

Reviews WhatsApp draft messages before sending, flags repetition, risky phrasing, apologies and formatting issues, and returns a score with suggested corrections.

Instructions

Revisa um rascunho SEM enviar: repetição contra as últimas mensagens do chat, dois-pontos e outros tells, auto-incriminação, desculpa, tratamento. Devolve ok/score/hits/sugestoes. No modo 'confirmar', revise, corrija e só então mostre o texto ao operador.

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>",
      "baloes": "<baloes>"
    },
    "name": "revisar_texto"
  }
}

Input Schema

Name	Required	Description	Default
`grupo`	Yes	slug, nome exato ou jid do chat
`baloes`	Yes	rascunho, um item por balão

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full burden and it does disclose the most important trait: it does not send anything. It also states the return payload (ok/score/hits/sugestoes) and the two-phase behavior in 'confirmar' mode. It does not say whether the review itself persists state or has side effects, which is a residual gap for an unannotated tool.

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?

Dense but front-loaded: the no-send constraint and the check list come first, followed by the return shape and the mode caveat. The telegraphic style ('dois-pontos e outros tells', 'tratamento') is compact, though the abruptness costs a little clarity.

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 two-parameter analysis tool with no output schema, the description covers what it checks, that it does not send, and the shape of the result, which is sufficient to call it correctly. The only loose end is the unparameterized 'confirmar' mode, whose activation mechanism is left unexplained.

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 parameters (grupo, baloes) are already documented, and the description adds little about them beyond 'um item por balão' being implicit. It instead references a 'modo confirmar' that is not among the parameters, which could leave the agent unsure how that mode is set.

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 specific verb and resource ('Revisa um rascunho') immediately qualified by the key scope fact 'SEM enviar', which separates it from sending-oriented siblings. It then enumerates the exact checks performed (repetition vs. recent chat messages, colons/tells, self-incrimination, apology, forms of address), so an agent knows precisely what the tool does.

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?

Usage is clear from context: run this on a draft before it is sent, and in 'confirmar' mode review, correct, then show the text to the operator. What is missing is an explicit naming of the alternative path (e.g. when to skip review and call a send/reply tool directly), so alternates are only implied.

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