Skip to main content
Glama
HOCGuard

HOC Guard MCP

by HOCGuard
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

guard_create_purpose

Create a draft data-processing purpose in Guard—nothing goes live until a person reviews and releases it—by defining data use, consent text, and legal basis.

Instructions

Cria uma finalidade nova na conta do Guard como RASCUNHO (proposta do agente). Nada vai ao ar: a pessoa revisa e clica em Liberar na tela do Guard. Descreva o uso do dado, o texto que a pessoa vai ler e a base legal. Regras checadas antes de enviar: legítimo interesse não vale com dado sensível (use consentimento) e exige o teste nas 3 fases (lia_interest, lia_necessity, lia_balance) e como se opor (lia_opt_out). Consulte guard_list_purposes antes para não duplicar. Exige guard_login com permissão de edição.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lawNoLei do contexto: br (LGPD) ou eu (GDPR). Padrão: br.
scopeNoEscopo: quem são os titulares e onde o dado é coletado.
titleYesNome curto da finalidade. Ex: "Envio de newsletter".
agenteNoNome do agente, aparece para a pessoa na proposta. Ex: "Claude Code".
minorsNoEnvolve dado de criança ou adolescente.
resumoNoPor que o agente propõe esta finalidade (ex: onde no código o dado é coletado).
rationaleNoJustificativa da base legal escolhida.
sensitiveNoEnvolve dado pessoal sensível (saúde, biometria, religião, origem racial etc).
descriptionYesPara que o dado é usado, em linguagem simples.
legal_basisYesBase legal: consent, legitimate_interest, contract ou legal_obligation.
lia_balanceNoFase 3: balanceamento com as expectativas e direitos da pessoa.
lia_opt_outNoComo a pessoa se opõe ao tratamento. Obrigatório com legítimo interesse.
consent_textYesTexto que a pessoa (titular) lê no ponto de coleta.
lia_interestNoLegítimo interesse, fase 1: qual é o interesse e de quem.
lia_necessityNoFase 2: por que é necessário e não há meio menos invasivo.
lia_conclusionNoConclusão do teste de legítimo interesse.
lia_safeguardsNoSalvaguardas adotadas (minimização, pseudonimização, prazo curto).
retention_daysNoPor quantos dias o dado é guardado.
retention_startsNoA partir de quando a retenção conta (ex: fim do contrato, último acesso).
grouping_identifierNoComo o titular é identificado.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare non-readonly, non-idempotent, non-destructive. The description goes well beyond that: nothing is published, a human reviews and clicks 'Liberar', validation rules run before submission, and the LIA phase requirements (lia_interest, lia_necessity, lia_balance, lia_opt_out) are enumerated. That is substantial behavioral context.

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-loaded with the mutate-draft fact and the human-approval flow, followed by preconditions and validation rules. Dense but each sentence carries distinct information; slightly long but nothing is wasted.

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 20-parameter mutation tool with no output schema, the description covers the flow, preconditions, and conditional validation rules. Minor gaps remain (e.g., what is returned after draft creation, whether the draft is editable later), but nothing that would block correct invocation.

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 100%, so the baseline is 3, but the description adds conditional dependency semantics the schema only implies: legitimate_interest requires the three LIA phases plus opt-out, and consent is required when sensitive data is involved. This meaningfully exceeds the flat per-field descriptions.

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?

Specific verb ('cria') plus resource ('finalidade nova na conta do Guard') plus mode ('como RASCUNHO'). It implicitly separates itself from guard_update_purpose, guard_get_purpose, and guard_list_purposes by naming the draft-creation act.

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?

Explicit prerequisites and ordering: consult guard_list_purposes first to avoid duplicates, and requires guard_login with edit permission. It also states when a legal basis is invalid ('legítimo interesse não vale com dado sensível'), which is directly actionable guidance.

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

Deploy Server

Other Tools