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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds useful behavioral context beyond those: the National Weather Service as source, JSON output format, the 48-hour window, and the $0.003 pricing. This is enough context for a read-only weather lookup, though it omits details like unit conventions or coordinate format.

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?

The description is one dense, front-loaded sentence followed by short factual tags (source, format, price). Every phrase adds information, and there is no filler or repetition of schema content.

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?

For a read-only, two-required-parameter tool, the description covers the data available, the geographic scope, the time range, source, and response format. It lacks a few details such as units or timezone behavior, but the missing information is unlikely to prevent 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 description coverage is 100%, so the schema already documents lat, lon, and hours. The description adds only minor semantics—'US coordinate' for lat/lon and 'next 48 hours' aligning with the hours parameter. That is helpful but does not substantially extend what the schema already provides.

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?

The description is precise: 'US hourly forecast (NWS)' plus 'Hour-by-hour forecast for any US coordinate: temperature, precipitation chance, wind, conditions for the next 48 hours.' It names the resource, the data fields, and the horizon, and it is clearly distinguishable from weather_current, weather_forecast, weather_metar, and weather_alerts.

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?

The description makes the intended use case obvious: when an agent needs an hour-by-hour weather forecast for a US location. It also implies the non-US exclusion via 'US coordinate.' However, it does not explicitly point to sibling alternatives such as weather_current or weather_forecast, so it stops short of perfect routing guidance.

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