Skip to main content
Glama

colegios.shop — uniformes escolares

Armar el kit del grado

armar_kit
Read-onlyIdempotent

EN UN SOLO PASO: el kit armado por la tienda (ej. "1er grado", "invierno") con un talle o la edad → link al carrito. Lo que no tiene stock o talle queda afuera con aviso. Si no se indica kit y hay varios, devuelve la lista. NO compra ni cobra.

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": {
      "slug": "<slug>"
    },
    "name": "armar_kit"
  }
}

Input Schema

NameRequiredDescriptionDefault
kitNoNombre, grupo o id del kit
edadNoEdad del chico en años (opcional). Sólo sirve para sugerir el talle si la tienda tiene prendido el ayudante de talle.
slugYesIdentificador de la tienda (lo que va después de colegios.shop/t/).
talleNo

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?

Goes beyond the annotations by disclosing that out-of-stock or unavailable-size items are dropped from the kit with a notice, and that an omitted kit parameter yields a list of candidates. The "NO compra ni cobra" line reinforces rather than contradicts readOnlyHint/destructiveHint=false. It does not cover error behavior for an unknown slug or kit name.

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?

The "EN UN SOLO PASO" lead front-loads the core value, and each following sentence covers a distinct behavior (exclusion with notice, ambiguous-kit fallback, no purchase). Dense but with no filler; the all-caps emphasis is slightly noisy but not wasteful.

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?

With no output schema, the description carries the return contract and does it well: a cart link, a list when the kit is ambiguous, and a notice for excluded items. Only the failure mode for an unrecognized slug or kit is left unspecified.

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 already 75%, but the description adds real meaning: kit and talle/edad are the choice inputs, and edad is only a size-suggestion aid. The one undocumented parameter (talle) is at least referenced as a valid alternative to edad.

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?

States a concrete verb and resource: assembles the store-curated kit (e.g. "1er grado", "invierno") with a size or age and returns a cart link. It implicitly separates itself from armar_pedido by saying it does not buy or charge, though it never names the sibling armar_carrito_por_texto to clarify the kit-vs-free-text distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Describes the fallback path (if no kit is given and there are several, it returns the list), which implies when the tool is usable, and the closing "NO compra ni cobra" rules out use as a checkout step. But there is no explicit when-to-use-this-vs-alternatives guidance against armar_carrito_por_texto or armar_pedido.

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.

Resources