Ficha completa de un plan por su nombre exacto: precio, ciclo, recursos, de qué fuente salió cada dato y cuándo se leyó. Si el plan no está en el catálogo devuelve null: eso significa que no se puede comprar, aunque alguna página lo anuncie.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the bar is lowered. The description adds genuine value beyond annotations: the null-return semantics ('no se puede comprar, aunque alguna página lo anuncie') and data provenance disclosure (source and read time per datum), which are materially important for agent decisions.
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?
Two sentences, zero waste. The first is front-loaded with the purpose and return fields; the second handles the failure contract. Every clause earns its place, and the most decision-relevant fact (null means not purchasable) is given prominent placement.
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?
A single-parameter read tool with an output schema (which documents return fields), safety annotations, and a description that covers returned data plus null semantics is nearly complete. The only gap is explicit sibling routing, which overlaps dimension 2 rather than a missing behavioral fact.
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%, so the description must compensate. 'nombre exacto' adds the critical requirement of exactness, which warns the agent that approximate names will fail, but it does not add format details such as case sensitivity or whether a full display name or slug is expected. Partial but meaningful compensation.
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?
Description states a specific verb+resource ('get' a plan's full record) and defines the scope precisely: price, cycle, resources, data source, and read timestamp. It also establishes the null-return contract for non-catalog plans, which distinguishes it from search_products (discovery) and quote (pricing proposal).
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?
'por su nombre exacto' clearly implies this tool requires an exact name, which routes agents away from search_products when they lack it, but the alternative is never named and no explicit when-not-to-use guidance is given. The null interpretation is useful, but discovery routing is left implicit.
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.
Cada herramienta tiene un propósito claramente diferenciado: estado del catálogo, búsqueda, comparación, ficha, cotización, pedido, infraestructura, políticas y SLA. Aunque varias empiezan por get_, sus dominios no se solapan y las descripciones refuerzan cuándo usar cada una.
La mayoría sigue el patrón verbo_sustantivo en snake_case (search_products, compare_products, create_draft_order, get_product). Se desvían quote, que es solo un verbo, y catalog_status, que parece un sintagma nominal en lugar de get_catalog_status; son desviaciones menores y no generan confusión.
Nueve herramientas es un tamaño adecuado para un catálogo de hosting: cubren consulta, comparación, cotización y pedido sin llegar a ser un servidor de administración. Cada herramienta tiene un rol claro y ninguna sobra.
El flujo principal está completo: conocer la frescura del catálogo, buscar, comparar, obtener fichas, cotizar y crear un pedido en borrador, además de las consultas legales, de SLA e infraestructura. No se echan en falta operaciones de escritura porque el servidor es explícitamente de consulta y no cobra ni contrata.