Skip to main content
Glama
Auditor DIAN

Auditor DIAN

by RafaGM1108

Registrar cliente

crear_cliente

Registers a new client using NIT/ID and name so their invoices can be loaded and queried; if the client exists, returns their history unchanged.

Instructions

Registra un cliente nuevo en este equipo para poder cargar y consultar sus facturas.

Úsela cuando el usuario diga, por ejemplo:

  • "Crea el cliente 900.000.009-9, Mi Cliente SAS"

  • "Sí, créalos" después de que ingerir_por_cliente informe compradores sin cliente: use el NIT y el nombre que esa herramienta devolvió.

Si el cliente ya existe no cambia nada y devuelve su historial (creado: false). Si otro cliente tiene el mismo nombre con otro NIT, lo avisa: puede ser un NIT mal escrito y conviene confirmarlo con el usuario.

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": {
      "cliente": "<cliente>",
      "nombre": "<nombre>"
    },
    "name": "crear_cliente"
  }
}

Input Schema

NameRequiredDescriptionDefault
nombreYesNombre o razón social del cliente.
clienteYesNIT o cédula del cliente, tal como lo escriba el usuario: con puntos, espacios, guion, 'NIT' o 'C.C.', con o sin dígito de verificación. Si lo nombra por su razón social, búsquelo antes con listar_clientes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.1

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: idempotency (an existing client changes nothing), the returned signal (`creado: false`) plus the prior history, and a fuzzy-duplicate warning path. That is exactly the context annotations cannot express.

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?

Purpose is front-loaded in the first sentence, followed by trigger examples and edge-case behavior in a compact order. The bulleted example block is useful for agent matching, though the definition runs longer than strictly necessary and could carry the NIT-format hint itself instead of relying on the schema.

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

Completeness5/5

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

For a two-parameter create tool with no output schema, the definition covers the write side effect, idempotency, partial return shape, and the ambiguous-duplicate case. An agent has everything needed to call it correctly and to know when to pause for confirmation.

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% and the schema already documents the accepted NIT/C.C. formats, so the baseline is 3. The description goes slightly beyond by prescribing where the values come from in the ingest flow (the NIT and name returned by ingerir_por_cliente), but it adds no format or validation detail not already in the schema.

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?

Uses a specific verb plus resource ('Registra un cliente nuevo en este equipo') and states the downstream goal (para poder cargar y consultar sus facturas), which tells an agent exactly what side effect to expect. Sibling differentiation is only partial: it references ingerir_por_cliente as a data source, but never contrasts itself with listar_clientes (that routing hint lives in the schema, not the description).

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?

Gives concrete trigger phrases ("Crea el cliente 900.000.009-9, Mi Cliente SAS") and a non-obvious workflow case: after ingerir_por_cliente reports buyers without a client, use the NIT and name that tool returned. It also states when to stop and confirm with the user (same name, different NIT), which is explicit when-to-use and when-to-ask guidance.

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