Skip to main content
Glama
Sign In

Atalaya · Los riesgos de tu ciudad

by io.lapoliza
OverviewDiscussionsAdmin

Perfil de riesgo de un lugar (cuadro de 150 m)

perfil_cuadro
Read-onlyIdempotent

Qué tan expuesto está un lugar de Colombia en general, no solo ahora: perfil del cuadro de 150 m que contiene el punto. Trae el riesgo general (suma de riesgos de 8 familias: agua, terreno, sismo y, cuando se publique lo observado en la calle, vías, peatones y ciclistas, redes eléctricas, árboles y obras; medio suma 1 y alto 2, con cuántas familias tienen dato), la amenaza oficial principal (POT de Bogotá y Medellín, estudios y manchas de La Niña del IDEAM) comparada con el resto del municipio, la zona sísmica de la NSR-10 y el suelo de la microzonificación de Bogotá, el relieve, lo que pasa ahora en el cuadro (lluvia, crecientes, pronóstico, sismos con su intensidad), la gente expuesta (DANE 2018 y estimado 2026, viviendas, edificios) y los eventos de los últimos 12 meses. Acepta un lugar en texto, coordenadas o el código del cuadro (columna:fila). Úsala cuando alguien pregunte si una zona es riesgosa, si se inunda, si tiene amenaza de deslizamiento o de sismo, o antes de recomendar un seguro para un sitio. Es por cuadro, no por predio.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "perfil_cuadro"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitud (alternativa a lugar).
lonNoLongitud (alternativa a lugar).
celdaNoCódigo del cuadro, columna:fila (p. ej. el que devuelve consultar_riesgo).
lugarNoDirección, barrio o sitio en Colombia (incluye la ciudad si no es Bogotá). Mejor una dirección que un barrio: el perfil es del cuadro de 150 m donde cae el punto.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, but the description goes well beyond them: it discloses the scoring scheme ('medio suma 1 y alto 2, con cuántas familias tienen dato'), the provenance of each layer (POT Bogotá/Medellín, IDEAM La Niña, NSR-10, microzonificación, DANE 2018 and 2026 estimate), the comparative baseline against the municipality, and the 12-month event window. That is substantive context an agent cannot infer from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the opening clause, which is good, but the remainder is a single run-on sentence dense with semicolon-separated enumerations and nested parentheses. Almost every clause carries real data content, so little is pure filler, yet the lack of structure makes it hard to scan for the fields an agent actually needs.

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?

There is no output schema, so the description carries the full burden of explaining return values, and it does: risk totals with family counts, official hazard versus municipal comparison, seismic zone and soil, relief, current conditions, exposed population, and recent events. For a four-parameter, open-world read tool this leaves nothing essential an agent needs before calling it.

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?

Schema coverage is 100%, so each of lat/lon/celda/lugar is already documented, including the 'alternativa a lugar' relationship. The description adds only a light confirmation that any of the three input forms is accepted ('texto, coordenadas o el código del cuadro'), without new format rules or precedence when several are supplied. Baseline 3 applies since the schema does the heavy lifting.

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 resource and scope: 'perfil del cuadro de 150 m que contiene el punto', and enumerates the concrete contents (risk sum over 8 families, official hazard, NSR-10 seismic zone, microzonificación, relief, live conditions, exposed population, 12-month events). It also draws the key boundary against finer-grained tools with 'Es por cuadro, no por predio' and 'en general, no solo ahora', so an agent can separate it from siblings without opening a 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?

Explicit trigger conditions are given: 'Úsala cuando alguien pregunte si una zona es riesgosa, si se inunda, si tiene amenaza de deslizamiento o de sismo, o antes de recomendar un seguro'. The scope caveat (per cell, not per property) further narrows usage. It stops short of naming the alternatives consultar_riesgo or explicar_cobertura and when to prefer them, so routing between siblings is only implied.

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

All Atalaya · Los riesgos de tu ciudad toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources