Skip to main content
Glama

Conferir provas contra as regras

conferir_provas
Read-only

Validates extracted document evidence and order, tracking, conversation, and log data against YouShop rules, returning a checklist, verdict, alerts, and corrections to fix.

Instructions

Roda o motor de regras da YouShop (Cláusula 8: 8.5 completude, 8.9 prazo, 8.10 recusas) sobre o que você extraiu das imagens e os dados do servidor (pedido, rastreio, conversas, logs). Retorna checklist, veredito, alertas e o que corrigir. A DECISÃO É DAS REGRAS, NÃO DO MODELO: apresente o veredito e os motivos como retornados, sem suavizar nem contradizer.

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": {
      "contestacao_id": "<contestacao_id>",
      "provas_extraidas": "<provas_extraidas>"
    },
    "name": "conferir_provas"
  }
}

Input Schema

NameRequiredDescriptionDefault
contestacao_idYesID da contestação, ex.: CB-002
provas_extraidasYesUm item por documento lido em buscar_documentos, com o que foi extraído de cada imagem

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Beyond readOnlyHint=true, it discloses the return contents (checklist, veredito, alertas, o que corrigir) and a critical behavioral constraint: the verdict belongs to the rules, not the model, and must be reported without softening or contradicting it. It does not say what happens when rules fail or data is missing, which keeps it from 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?

Three sentences, front-loaded with what runs and on what, then returns, then the non-negotiable presentation rule. No filler or repetition of the title.

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 no output schema, the description carries the burden of describing returns and does so (checklist, veredito, alertas, correções). For an evaluation tool with 100% schema coverage this is nearly complete, missing only failure/error behavior.

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%, so the schema already documents contestacao_id and every field of provas_extraidas. The description only generically refers to 'o que você extraiu das imagens', adding no format or constraint details beyond the schema; 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?

States a specific verb and resource ('Roda o motor de regras da YouShop') and names the exact clauses it applies (8.5 completude, 8.9 prazo, 8.10 recusas), plus the inputs it consumes. This clearly separates it from the retrieval siblings, which only fetch data.

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?

Makes the precondition explicit by saying it runs over 'o que você extraiu das imagens e os dados do servidor', implying you must first call buscar_documentos and the other lookup tools. It stops short of naming an alternative or a when-not-to-use condition, but among these siblings it is the only evaluation tool, so the guidance is clear.

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