Audita um lote JSON com regras locais e contexto da operadora. Quando usar: para identificar inconsistências administrativas. Quando não usar: para aplicar correções; use tiss_apply_fixes.
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| lote | Yes | ||
| contexto | No | ||
| operadora | No |
| Name | Required | Description | Default |
|---|---|---|---|
| valid | Yes | ||
| decisao | No | ||
| version | Yes | ||
| findings | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / operadoraAdded value: +{
+ "pattern": "^[0-9]{5,6}$",
+ "type": [
+ "string",
+ "object"
+ ]
+}Output schema / properties / decisaoAdded value: +{
+ "additionalProperties": false,
+ "properties": {
+ "needs": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "rules": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "id": {
+ "type": "string"
+ },
+ "mantenedor": {
+ "additionalProperties": false,
+ "properties": {
+ "registro_ans": {
+ "type": "string"
+ },
+ "tipo": {
+ "enum": [
+ "comunidade",
+ "operadora"
+ ]
+ }
+ },
+ "required": [
+ "tipo"
+ ],
+ "type": "object"
+ },
+ "source": {
+ "additionalProperties": false,
+ "properties": {
+ "acesso": {
+ "type": "string"
+ },
+ "data": {
+ "type": "string"
+ },
+ "official": {
+ "type": "boolean"
+ },
+ "titulo": {
+ "type": "string"
+ },
+ "url": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "url",
+ "titulo",
+ "data",
+ "acesso",
+ "official"
+ ],
+ "type": "object"
+ }
+ },
+ "required": [
+ "id",
+ "source",
+ "mantenedor"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "tipo": {
+ "enum": [
+ "aprovar_por_regra",
+ "pendente",
+ "encaminhar_auditor"
+ ]
+ }
+ },
+ "required": [
+ "tipo",
+ "rules",
+ "needs"
+ ],
+ "type": "object"
+}Output schema / properties / findings / items / properties / code / enumPrevious value: -[
- "audit.autorizacao_ausente",
- "audit.autorizacao_vencida",
- "audit.carteirinha_ausente",
- "audit.carteirinha_inativa",
- "audit.carteirinha_vencida",
- "audit.data_ausente",
- "audit.operadora_divergente",
- "audit.procedimento_ausente",
- "audit.procedimento_fora_da_tabela",
- "audit.tabela_fora_de_vigencia",
- "audit.tabela_sem_procedimentos",
- "audit.valor_nao_positivo",
- "guia.carteirinha_ausente",
- "guia.executante_ausente",
- "guia.sequencial",
- "item.valor_divergente",
- "item.valor_zerado",
- "lote.acima_do_teto",
- "lote.caractere_invalido",
- "lote.estrutura",
- "lote.guia_duplicada",
- "lote.hash_divergente",
- "lote.valor_total_geral",
- "lote.vazio",
- "regra.combinacao_proibida",
- "regra.max_itens",
- "regra.obrigatorio",
- "regra.padrao",
- "regra.valores",
- "tuss.fora_de_vigencia",
- "tuss.inexistente",
- "versao.divergente",
- "versao.nao_detectada",
- "versao.nao_suportada",
- "xml.doctype",
- "xml.encoding",
- "xml.malformado",
- "xsd.atributo",
- "xsd.elemento_ausente",
- "xsd.elemento_inesperado",
- "xsd.enumeracao",
- "xsd.outro",
- "xsd.padrao",
- "xsd.tamanho",
- "xsd.tipo"
-]New value: +[
+ "audit.autorizacao_ausente",
+ "audit.autorizacao_vencida",
+ "audit.carteirinha_ausente",
+ "audit.carteirinha_inativa",
+ "audit.carteirinha_vencida",
+ "audit.data_ausente",
+ "audit.operadora_divergente",
+ "audit.procedimento_ausente",
+ "audit.procedimento_fora_da_tabela",
+ "audit.tabela_fora_de_vigencia",
+ "audit.tabela_sem_procedimentos",
+ "audit.valor_nao_positivo",
+ "autorizacao.carteirinha",
+ "autorizacao.dado_ausente",
+ "autorizacao.exige_auditoria",
+ "autorizacao.sem_regra",
+ "guia.carteirinha_ausente",
+ "guia.executante_ausente",
+ "guia.sequencial",
+ "item.valor_divergente",
+ "item.valor_zerado",
+ "lote.acima_do_teto",
+ "lote.caractere_invalido",
+ "lote.estrutura",
+ "lote.guia_duplicada",
+ "lote.hash_divergente",
+ "lote.valor_total_geral",
+ "lote.vazio",
+ "regra.combinacao_proibida",
+ "regra.exige_autorizacao",
+ "regra.max_itens",
+ "regra.obrigatorio",
+ "regra.padrao",
+ "regra.valores",
+ "tuss.fora_de_vigencia",
+ "tuss.inexistente",
+ "versao.divergente",
+ "versao.nao_detectada",
+ "versao.nao_suportada",
+ "xml.doctype",
+ "xml.encoding",
+ "xml.malformado",
+ "xsd.atributo",
+ "xsd.elemento_ausente",
+ "xsd.elemento_inesperado",
+ "xsd.enumeracao",
+ "xsd.outro",
+ "xsd.padrao",
+ "xsd.tamanho",
+ "xsd.tipo"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. The "to apply corrections use tiss_apply_fixes" clause implies this tool does not mutate, which is a useful signal, but it never states that explicitly and says nothing about which local rules run, determinism, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences with the purpose front-loaded and the use/no-use guidance structured and clearly separated. Every sentence carries distinct information with no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists so return values needn't be described, and the routing guidance is present. However, for a complex tool with nested objects, 0% schema coverage and no annotations, the description leaves what inputs are needed and what the audit checks largely unexplained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across 4 parameters including nested contexto and operadora objects. The description only mentions lote and "contexto da operadora" generically; it does not explain data, operadora format, or the nested contexto fields, so the parameter gap is largely unaddressed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ("Audita") and resource ("lote JSON"), plus scope (regras locais e contexto da operadora). It explicitly distinguishes from tiss_apply_fixes, but not from the close sibling tiss_validate, so its role among the validation-family tools remains partly ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Contains explicit "Quando usar" (identify administrative inconsistencies) and "Quando não usar" (to apply corrections) clauses, and names the alternative tool (tiss_apply_fixes). The routing decision is fully stated, not inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.