Skip to main content
Glama

busqueda_universal

Read-only

Searches one term across ten Chilean state agencies and a Hugging Face dataset, returning literal text and ready-to-use citations for legal research.

Instructions

Busca un término a la vez en el dataset de Hugging Face y en los 10 organismos del Estado (BCN, CGR, DT, PJUD, TC, CNE, Panel de Expertos, CMF, SII, SMA/TDLC), devolviendo los resultados con sus citas listas y texto literal.

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": {
      "consulta": "<consulta>"
    },
    "name": "busqueda_universal"
  }
}

Input Schema

NameRequiredDescriptionDefault
consultaYesTérmino o frase a buscar

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.11.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety and external-world reach are covered. The description adds useful context — the search spans 10 state bodies plus a Hugging Face dataset, and results come back with citations and literal text — but says nothing about result ranking, volume limits, pagination, latency, or behavior when a source fails.

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?

A single front-loaded sentence that leads with the verb and scope; the long parenthetical list of 10 organisms is dense but genuinely informative. No filler sentences or restated name/title.

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 does the necessary work of saying what comes back (results with citations and literal text), which an agent needs for downstream reasoning. Remaining gaps — result caps, ordering across the 10 sources, and error behavior — are minor for a one-parameter read-only search.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter exists and schema description coverage is 100% ('Término o frase a buscar'), so the schema already carries the meaning and a 3 baseline applies. The description adds a mild constraint via 'un término a la vez', but gives no guidance on syntax, phrase quoting, accents, or boolean operators.

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 concrete verb (busca) and scope (Hugging Face dataset plus the 10 named state organisms), and enumerates the sources so the agent knows this is a cross-organism search rather than a per-organism one. The return deliverable (results with ready citations and literal text) is also stated, making the tool clearly separable from siblings like cgr_search_jurisprudencia or cmf_buscar_sanciones.

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?

The phrase 'un término a la vez' implies an invocation constraint (one query per call), but there is no explicit when-to-use guidance, no statement of when to prefer a targeted sibling search over this broad one, and no prerequisites or exclusions. Usage is inferable but not spelled out.

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

Deploy Server

Other Tools