Skip to main content
Glama
verificar-curp-mcp

verificar-curp-mcp

by rcfrias

Crear enlace de captura

crear_enlace_captura

Create a single-use link so a client can enter their CURP from their phone; validate it, optionally cross-check reservation data, and send the result to a configured destination.

Instructions

Crea un enlace de un solo uso para que un cliente escriba su CURP desde su celular (por ejemplo, en el check-in). Si mandas persona (los datos de la reservación), la CURP se coteja contra ellos sin mostrárselos al cliente; con ask_guest_persona el cliente también escribe su nombre y fecha de nacimiento. El resultado NO llega a esta conversación: se entrega al destino destination_id (webhook, correo o chat configurado en el panel de verificarcurp.com → Destinos), solo si la CURP es válida y coincide. Crear el enlace es gratis; cada respuesta del cliente consume 1 token (hasta 3 intentos). Máximo 20 enlaces vivos a la vez. Devuelve url (compártela solo con el cliente) y expiresAt.

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": {
      "destination_id": "<destination_id>"
    },
    "name": "crear_enlace_captura"
  }
}

Input Schema

NameRequiredDescriptionDefault
personaNoDatos de la reservación para cotejar la CURP que escriba el cliente
referenceNoTu referencia (reserva, folio); viaja con la entrega. Nunca pongas la CURP aquí.
destination_idYesID del destino (panel → Destinos)
ask_guest_personaNoPedir también nombre, primer apellido y fecha de nacimiento al cliente

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false): it discloses that the result does NOT return to this conversation but is delivered asynchronously to `destination_id`, only when the CURP is valid and matches, that link creation is free but each response costs 1 token up to 3 attempts, and that at most 20 live links may exist.

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, followed by mode behavior, delivery mechanics, cost/limits, and return values in a single dense block. Every sentence carries information, though it is longer than strictly minimal; nothing is filler, but it is not a tight two-liner either.

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 fairly complex async tool with no output schema, the description covers the full picture: async delivery target, cost and attempt/token limits, link cap, and the returned `url` and `expiresAt` along with the caution to share the URL only with the client. Nothing an agent needs to invoke it correctly is missing.

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 genuine semantics: `persona` is matched against the typed CURP without ever being shown to the client, `ask_guest_persona` additionally collects name and DOB, and `destination_id` is characterized as the configured webhook/email/chat target.

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 and resource: creates a single-use link for the client to type their CURP from their phone. It is unmistakably a link-creation tool, clearly distinct from validation siblings like validar_curp or verificar_curp_renapo, so an agent can select it without opening the schema.

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 a concrete context for use (e.g., at check-in) and explains the two modes via `persona` and `ask_guest_persona`. However, it never names an alternative tool or states when NOT to use it (e.g., when you already have the CURP and just want to validate it), leaving the routing decision to inference.

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