Skip to main content
Glama
Safefy-Pay

Safefy MCP

Official
by Safefy-Pay

Create Customer

safefy_payment_create_customer
Destructive

Creates a customer in the Safefy payment API from provided name, email, and optional document or address data.

Instructions

Cria um cliente na API agora. Não pergunte 'via API ou painel' nem 'qual framework' — você JA ESTÁ conectado à API. Se o usuário disser 'cria cliente chamado Jorge', chame esta tool com name='Jorge'. Dados mínimos: name. Email, documento e outros são opcionais. Não pede merchant ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
emailYes
phoneNo
documentNo
metadataNo
externalIdNo
addressCityNo
addressStateNo
documentTypeNo
addressNumberNo
addressStreetNo
addressCountryNo
addressComplementNo
addressPostalCodeNo
addressNeighborhoodNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.0
    • changedInput schema / properties / email / pattern
      Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
  2. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is mostly covered. The description adds that the agent is already connected to the API and should not request a merchant ID, but omits side effects, permissions, and response behavior.

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?

Front-loads purpose and is reasonably short, with an example that helps the agent act. Some conversational instruction lines are useful for behavior, though 'Não pede merchant ID' is marginal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter create tool with no schema descriptions and no output schema, the description is far from complete. It gives a minimal example and says not to ask about merchant ID, but incorrectly marks email optional and omits nearly all optional field semantics.

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

Parameters1/5

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

Schema description coverage is 0% with 15 parameters, so the description carries the full burden. It says only name is minimum and email/document/others are optional, but the schema requires email; this misleads on a required field and ignores most other parameters such as phone, address fields, metadata, externalId, and documentType.

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 'Cria' and resource 'cliente' and clarifies it acts directly on the API, not via panel or framework. The concrete example routes a user request to this tool and distinguishes the create operation from sibling customer tools.

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?

Tells the agent not to ask about API-vs-panel or framework and gives a concrete example for when to call it with name='Jorge'. It provides clear context but does not explicitly say when to prefer update_customer, get_customer, or list_customers instead.

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