Skip to main content
Glama

Elden — Jurisprudência e Legislação Brasileira (MCP)

contexto_gravar

Destructive

GRAVAR OU APAGAR (escrita; só use quando o advogado pedir ou quando for útil nas próximas conversas). acao = "memoria_guardar" (grava automático por padrão; texto até 600 caracteres, etiqueta = processo|tese|precedente|estilo|foro|prazo|cliente|outro, chave = número CNJ ou nome do cliente; não guarde CPF, peça inteira nem o que ele pediu para não registrar; passe id + confirmado=True para atualizar), "memoria_apagar" (id + confirmado=True), "estilo_criar" (nome + um de: base="padrao" para clonar, amostra=<texto da peça dele>, descricao/tipografia ou estilo_json; mostra prévia com confirmado=False e grava com confirmado=True), "estilo_editar" (nome + alteracoes_json + confirmado=True ao sobrescrever; novo_nome opcional), "estilo_apagar" (nome + confirmado=True), "memoria_modo" (texto="manual" ou "automatico" para alternar confirmação antes de novas lembranças), "relatar_problema" ou "feedback". Memória e estilo gravam só para este advogado.

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": {
      "acao": "<acao>"
    },
    "name": "contexto_gravar"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
acaoYes
baseNo
nomeNo
tipoNomelhoria
chaveNo
textoNo
amostraNo
consultaNo
esperadoNo
etiquetaNooutro
mensagemNo
descricaoNo
gravidadeNoatrapalha
novo_nomeNo
confirmadoNo
ferramentaNo
tipografiaNo
estilo_jsonNo
alteracoes_jsonNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description goes beyond that by disclosing the two-step confirmation convention (confirmado=False previews, True persists), the 600-character cap, the default auto-save behavior for memory, and the privacy scope ('Memória e estilo gravam só para este advogado'). Missing is whether deletion is irreversible or recoverable; the description never says what an apagar actually destroys.

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

Conciseness3/5

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

The lead clause is well front-loaded, but the body is a single run-on parenthetical cramming eight action variants into one sentence, which makes scanning harder than a short per-action list. The length is defensible given the number of modes, yet the formatting costs readability rather than earning every clause.

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

Completeness3/5

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

For a 20-parameter, eight-mode tool with zero schema descriptions, the description covers the memory and style flows well and notes the per-lawyer storage scope. However it never maps the remaining parameters to the relatar_problema/feedback actions or explains how the confirmation loop terminates, so an agent still has to guess on several execution paths.

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 0%, so the description carries the full burden and does substantial work: it defines `id`, `confirmado`, `texto` (max 600 chars), `chave` (CNJ number or client name), `etiqueta` (supplies the enum processo|tese|precedente|estilo|foro|prazo|cliente|outro that the schema lacks), plus `base`, `amostra`, `descricao`, `tipografia`, `estilo_json`, `alteracoes_json`, and `novo_nome`. Roughly six parameters (tipo, consulta, esperado, gravidade, mensagem, ferramenta) are left undocumented despite affecting the relatar_problema/feedback paths.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with an explicit verb pair ('GRAVAR OU APAGAR') and a write-mode marker, then enumerates the concrete `acao` values (memoria_guardar, memoria_apagar, estilo_criar/editar/apagar, memoria_modo, relatar_problema, feedback). An agent can tell this is the write-side counterpart to a read tool. It does not explicitly name a sibling or draw the boundary, which keeps it from a 5.

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?

Gives an explicit gating condition: 'só use quando o advogado pedir ou quando for útil nas próximas conversas'. It also states per-action conditions (estilo_criar shows a preview with confirmado=False and saves with confirmado=True; confirmado=True required to overwrite) and exclusions ('não guarde CPF, peça inteira nem o que ele pediu para não registrar'). Strong, though it never states when NOT to use this tool in favor of a named alternative.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.