nws_forecast_hourly

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

While the annotations already communicate read-only, idempotent, and non-destructive behavior, the description adds useful detail: the period length, the forecast horizon, the included fields (temperature, wind, precip probability, short forecast), and the large response warning. This goes beyond the annotations by setting expectations for response size and content.

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 two sentences and immediately states what the tool returns, the time range, the content of each period, and the alternative for a lighter response. Every word adds value, and the information is front-loaded.

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?

Without an output schema, the description compensates by listing the forecast fields and the risk of a large payload, which is enough for a caller. It does not specify units, timezone, or pagination, but for this simple lat/lon lookup the description satisfies selection and basic invocation needs.

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?

The input schema already has 100% coverage for the two parameters ('lat' and 'lon') with descriptions, bounds, and examples. The tool description does not add new parameter-specific meaning, but given the schema is fully self-descriptive, a baseline of 3 is appropriate.

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 clearly identifies the specific verb ('Get'), resource ('hourly forecast'), and required inputs (lat/lon). It also distinguishes this tool from its nearest sibling by emphasizing the hourly granularity and ~156-hour horizon, which is concrete and actionable.

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 provides a clear alternative by saying 'Large response — consider nws_forecast for daily summaries,' which tells users when another tool may be better suited. It does not fully spell out all the conditions under which the hourly tool should or should not be used, but it gives enough directional guidance for an agent to make the right choice.

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