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

Annotations already declare readOnlyHint=true, and the description does not contradict this. The description adds meaningful behavioral context: it describes the return content (named periods, narrative text), the constraint that only 'forecast' type zones resolve, and the zone code pattern. This goes beyond the annotation without being excessive, though it omits potential error behaviors or rate limits, which are not critical given the read-only nature.

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 moderately long but every sentence carries useful information: primary purpose, return structure, integration hints, and a usage constraint. It is front-loaded with the core purpose and then elaborates. There is minimal redundancy; the only slightly verbose part is the explanation of the alert-to-forecast chain, but that is directly relevant for correct parameter selection.

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?

The description covers the essential aspects: what the tool does, how to obtain a valid parameter, what constraints exist, and the nature of the output. Since an output schema exists, the return format need not be fully explained. While it doesn't explicitly list alternate tools for comparison, it gives enough context to avoid confusion. The integration with sibling tools is well documented, making it complete for an agent's selection and 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%, providing a clear baseline. The description adds extra semantic value by explaining the zone ID pattern ('XXZ###'), giving a concrete example, and specifying how the ID can be obtained from other tools (as 'forecastZone' or from 'affectedZones'). This context helps the agent correctly construct the parameter beyond what the schema alone offers.

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 states a specific verb ('Get'), resource ('text forecast for a public NWS forecast zone'), and outcome (returns named periods with narrative text). It also gives concrete examples of zone codes and clearly distinguishes the zone-level forecast from other forecast types, making the tool's role unambiguous even among siblings like nws_get_forecast.

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 explains how to obtain a valid zone_id from sibling tools (nws_search_alerts, nws_find_stations) and explicitly restricts usage to affectedZones entries with type 'forecast', excluding 'county' and 'fire' types. While it doesn't explicitly compare to nws_get_forecast, it provides clear context for when this tool should be used, and the exclusion of non-forecast types gives actionable guidance.

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