Skip to main content
Glama

Omie

by io.github.mcp-dir
OverviewDiscussionsAdmin

omie_lancar

Atalho: lança uma conta a PAGAR ou a RECEBER em UMA chamada, resolvendo os códigos por NOME no servidor (fornecedor/cliente, categoria, conta corrente, projeto, departamentos). Substitui o fluxo de 4-5 chamadas (list_customers + list_categories + list_checking_accounts + create). Aceita nome OU código em cada campo; se um nome não bater ou for ambíguo, retorna erro com as opções ANTES de criar (não chuta). Datas aceitam AAAA-MM-DD ou DD/MM/AAAA. • DUPLICIDADE: antes de criar, procura título do mesmo fornecedor com o mesmo vencimento e valor; se achar, NÃO lança e devolve os candidatos (passe ignorar_duplicidade:true pra lançar mesmo assim). • RATEIO: departamentos (centro de custo) e/ou categorias (várias categorias) com percentual OU valor por linha (todas no mesmo modo; percentuais somam 100). projeto por nome ou código. • PARCELAMENTO: parcelamento:{quantidade, periodicidade} cria N títulos (001/N…N/N) com o vencimento avançando a cada período; valor é o de CADA parcela (ou passe valor_por_parcela:false pra dividir o total). Cada parcela é uma chamada à Omie (loop interno): a resposta lista as criadas e os erros por parcela. Use isto por padrão pra lançar; as tools omie_create_* continuam pra quem já tem o payload completo.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tipoYes
valorYes
accountNo
projetoNo
categoriaNo
categoriasNo
fornecedorYes
observacaoNo
vencimentoYes
parcelamentoNo
data_previsaoNo
departamentosNo
conta_correnteYes
numero_documentoNo
ignorar_duplicidadeNo
codigo_lancamento_integracaoNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / categorias
      Added value: +{
+  "items": {
+    "properties": {
+      "categoria": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "number"
+          }
+        ]
+      },
+      "percentual": {
+        "type": "number"
+      },
+      "valor": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "categoria"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / departamentos
      Added value: +{
+  "items": {
+    "properties": {
+      "departamento": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "number"
+          }
+        ]
+      },
+      "percentual": {
+        "type": "number"
+      },
+      "valor": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "departamento"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / ignorar_duplicidade
      Added value: +{
+  "type": "boolean"
+}
    • addedInput schema / properties / parcelamento
      Added value: +{
+  "properties": {
+    "periodicidade": {
+      "enum": [
+        "semanal",
+        "quinzenal",
+        "mensal",
+        "bimestral",
+        "trimestral",
+        "semestral",
+        "anual"
+      ],
+      "type": "string"
+    },
+    "quantidade": {
+      "type": "number"
+    },
+    "valor_por_parcela": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "quantidade"
+  ],
+  "type": "object"
+}
    • addedInput schema / properties / projeto
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    }
+  ]
+}
    • changedInput schema / required
      Previous value: -[
-  "tipo",
-  "fornecedor",
-  "categoria",
-  "conta_corrente",
-  "valor",
-  "vencimento"
-]New value: +[
+  "tipo",
+  "fornecedor",
+  "conta_corrente",
+  "valor",
+  "vencimento"
+]
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare it is a write operation (readOnlyHint=false) and non-idempotent, but the description adds substantial behavior the annotations cannot: pre-creation duplicate detection with an override flag, ambiguity returns alternatives instead of guessing, date format acceptance, and — importantly — that parcelamento issues each parcela as a separate Omie call with per-parcela errors. It does not state auth/permission requirements, but disclosure is well above the annotation baseline.

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 single-paragraph summary followed by three dense bullets (DUPLICIDADE, RATEIO, PARCELAMENTO) and a closing routing sentence. Everything earns its place; the opening paragraph is long but packs distinct facts rather than filler.

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 16-parameter composite write tool with nested objects and no output schema, the description covers the failure modes an agent needs (duplication guard, ambiguity error, per-parcela partial failure) and what the response lists. A few simple fields and any permission prerequisites remain unaddressed, keeping it short of 5.

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 description coverage is 0% and 16 parameters, so the description must compensate. It does for the complex ones: nome-OU-código acceptance, categorias/departamentos rateio with percentual-ou-valor and the 100% sum rule, parcelamento fields (quantidade/periodicidade/valor_por_parcela) and whether valor is per-parcela, plus date formats. It leaves account, observacao, numero_documento, codigo_lancamento_integracao and data_previsao unexplained, but most are self-naming.

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 (lança/cria) and resource (conta a PAGAR ou a RECEBER), and goes further by naming the workflow it replaces (list_customers + list_categories + list_checking_accounts + create). An agent can distinguish it from omie_create_payable/omie_create_receivable immediately.

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 routing: "Use isto por padrão pra lançar; as tools omie_create_* continuam pra quem já tem o payload completo." This states both the default condition and the alternative with the condition that selects it.

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

All Omie toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources