Skip to main content
Glama

Buscar artículos del blog

buscar_articulos
Read-onlyIdempotent

Busca por palabras clave en los 34 artículos del blog de Autoridad Digital (en español): SEO avanzado, GEO, llms.txt, schema, entity SEO, agentes de IA y casos reales con datos de Search Console. USAR CUANDO: buscas una guía, un análisis o un caso que citar o enlazar. NO USAR PARA: definiciones breves (usa consultar_glosario), precios o servicios (usa servicios_y_precios) ni búsquedas en internet: solo busca en este blog. CÓMO BUSCA: en título, extracto, slug, términos del glosario y cuerpo de cada artículo. Basta con que contenga una de las palabras; salen antes los que contienen más, y a igualdad los que las tienen en el título. DEVUELVE: título, fecha ISO 8601, extracto y URL de cada artículo, de más a menos relevante. SIN RESULTADOS: no es un error; devuelve total: 0 y la URL del índice del blog. Solo responde con isError si la búsqueda no tiene ninguna palabra útil. LÍMITES: como máximo 10 resultados por llamada y sin paginación. Si total es igual a limite, puede haber más: sube limite (máx. 10) o cambia las palabras clave. No hace peticiones externas.

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": {
      "tema": "<tema>"
    },
    "name": "buscar_articulos"
  }
}

Input Schema

NameRequiredDescriptionDefault
temaYesPalabras clave, no una pregunta completa: «llms.txt», «agentes de IA», «citation decay». Sin importar mayúsculas ni acentos; se ignoran palabras vacías como «de» o «para».
limiteNoNúmero máximo de artículos a devolver, de 1 a 10. Por defecto, 5.

Output Schema

NameRequiredDescriptionDefault
totalYesNúmero de artículos devueltos en `resultados` (como máximo, `limite`)
resultadosYesDe más a menos relevante; vacío si no hay coincidencias

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedOutput schema / properties / resultados / description
      Added value: +"De más a menos relevante; vacío si no hay coincidencias"
    • addedOutput schema / properties / resultados / items / properties / extracto / description
      Added value: +"Resumen del artículo en una o dos frases"
    • addedOutput schema / properties / resultados / items / properties / fecha / description
      Added value: +"Fecha de publicación, ISO 8601"
    • addedOutput schema / properties / resultados / items / properties / url / description
      Added value: +"URL del artículo: la fuente que hay que citar o enlazar"
    • addedOutput schema / properties / total / description
      Added value: +"Número de artículos devueltos en `resultados` (como máximo, `limite`)"
  2. Changed3 schema fields changed
    • changedInput schema / properties / limite / description
      Previous value: -"Número máximo de resultados"New value: +"Número máximo de artículos a devolver, de 1 a 10. Por defecto, 5."
    • changedInput schema / properties / tema / description
      Previous value: -"Tema o palabras clave, p. ej. «llms.txt» o «agentes de IA»"New value: +"Palabras clave, no una pregunta completa: «llms.txt», «agentes de IA», «citation decay». Sin importar mayúsculas ni acentos; se ignoran palabras vacías como «de» o «para»."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "additionalProperties": false,
      +  "properties": {
      +    "resultados": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "extracto": {
      +            "type": "string"
      +          },
      +          "fecha": {
      +            "type": "string"
      +          },
      +          "titulo": {
      +            "type": "string"
      +          },
      +          "url": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "titulo",
      +          "fecha",
      +          "extracto",
      +          "url"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "total": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "total",
      +    "resultados"
      +  ],
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false and idempotentHint=true, and the description adds substantial context beyond them: which fields are searched, OR-matching with relevance ranking, the 10-result cap with no pagination, the heuristic that total == limite implies more results exist, and that zero results are not an error (total: 0 plus an index URL) unless the query has no usable words.

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?

Labeled sections (USAR CUANDO, NO USAR PARA, CÓMO BUSCA, DEVUELVE, SIN RESULTADOS, LÍMITES) are front-loaded and scannable. The DEVUELVE block partly restates the declared output schema, which is the only redundancy.

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 read-only search tool with an output schema, the definition covers triggering, alternatives, matching semantics, result ordering, empty-result behavior and result caps. An agent has everything needed to call it correctly and interpret a 0-result response.

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 real meaning: keyword matching is case- and accent-insensitive, stopwords are ignored, matching is OR-based across title, excerpt, slug, glossary terms and body, with title hits ranked higher. It also explains how to react to the limite ceiling, though the exact increment strategy is left implicit.

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?

The description states a specific verb and resource ("Busca por palabras clave en los 34 artículos del blog") and scopes the corpus with topics. It also names the domain boundary (only this blog), so an agent can distinguish it from consultar_glosario, servicios_y_precios and the rest 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 Guidelines5/5

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

Explicit "USAR CUANDO" and "NO USAR PARA" sections route the agent: glossary for short definitions, servicios_y_precios for pricing, and internet search is excluded. Both the positive trigger and the exclusions with named alternatives are present.

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