riesgos

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the description correctly spends its space on traits annotations cannot express: live data, named upstream sources, country-wide vs. city-specific coverage, the 3h/6h forecast horizon, and 'Sin datos personales'. Useful behavioral context beyond the structured fields.

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?

Front-loaded with the core purpose and then the usage trigger; nearly every clause carries information. The parenthetical source list makes the first sentence a long run-on, but each item helps an agent judge relevance, so the density is largely earned.

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?

No output schema, so the description must imply the return shape; enumerating the aggregated event types plus the forecast does that adequately. It could say more about how results are structured or ordered near the radius, but for a read-only lookup this is sufficient to call correctly.

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 coverage is 100%, so baseline is 3, but the description adds real value by showing accepted 'lugar' formats ('Suba, Bogotá', 'calle 80 con Boyacá', 'Envigado') and stating that coordinates are an alternative. radio_km is left entirely to the schema, which is acceptable.

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?

States a specific verb and resource ('Riesgos activos alrededor de un lugar de Colombia') and then enumerates exactly which datasets are aggregated (IDIGER, SIATA, USGS, NASA FIRMS, vecinos, Open-Meteo). An agent knows precisely what this returns 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.

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

Explicit trigger conditions: 'Úsala cuando alguien pregunte si hay riesgo, lluvia, inundación, sismo, incendio o problemas en una zona de Colombia o si va a llover en las próximas horas.' Clear positive guidance, but no exclusions or mention of the sibling explicar_cobertura as an alternative.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds real context on top: it previews the response structure (safety steps, typical coverage, exclusions) and explicitly disclaims pricing, which tells the agent what to expect from the payload and where not to route cost questions.

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?

One compact paragraph, front-loaded with the guide's purpose and scope, followed by the coverage list, the exclusion, and the valid values. The long type list is dense but earns its place as the de facto enum; only minor trimming would improve flow.

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?

With a single fully documented parameter, a complete annotation set and no output schema, the description supplies everything else an agent needs: what the tool returns, its jurisdictional scope (Colombia), what it omits (prices), and the accepted risk-type vocabulary. The only unused opportunity is naming the sibling, which is not essential for correct invocation.

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 coverage is 100%, so the baseline is 3, but the description adds value the schema does not: it lists the twelve valid risk types (lluvia, inundacion, sismo, vendaval, granizo, vial, deslizamiento, incendio, hueco, caida_objetos, obras, hurto) that the schema leaves as a free-form string with no enum. That enumeration materially reduces the risk of the agent passing an unhandled value.

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?

States a specific function (explanatory guide by risk type) and enumerates its three content blocks: immediate safety steps, which insurance policies usually cover the event, and what they usually don't cover. It clearly is not a pricing or quoting tool. It never mentions the sibling consultar_riesgo, so an agent cannot tell from the description alone why it would pick this over that one.

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?

'No da precios' is an explicit exclusion that steers the agent away from expecting quotes, and 'Guía informativa para Colombia' implies a general-advisory context. But there is no statement of when to prefer this over consultar_riesgo, and no prerequisites or entry conditions are given; usage is implied rather than directed.

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