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

Annotations only cover the read-only/idempotent/open-world profile, and the description adds substantive behavior the agent could not otherwise know: the upstream model, the 30-90 minute validity window, the poleward 5-degree fallback result, worldwide scope, explicit physical limitations, and a 1-credit cost. That is well beyond what the annotations supply.

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 question-style opener front-loads the user intent, followed by the mechanism, the secondary result, and then caveats in a logical order. Nearly every clause carries information, though the question framing and the following 'Returns the probability...' sentence slightly overlap.

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 no output schema, the description still conveys what comes back (overhead probability plus the best chance within 5 degrees poleward) and bounds the forecast's validity. For a two-parameter, read-only lookup, no essential calling information is missing.

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% and both parameters (lat, lon) are already documented with ranges, so the description adds little syntax-level meaning. It only reinforces that the output is tied to a specific point plus a poleward neighbour, which is marginal extra information.

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 names a specific verb and resource — the probability of aurora overhead at a given latitude and longitude — and attributes it to the NOAA SWPC OVATION model. It is clearly distinguishable from sibling space-weather tools such as kp_index_now, kp_forecast_3day, and solar_wind_speed, which report indices rather than location-specific probability.

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?

It frames the use case ('right now'), gives the forecast horizon (30-90 minutes), and explicitly rules out multi-day forecasting and daylight/cloud/moonlight effects, which implicitly routes the agent to kp_forecast_3day, cloud_cover_forecast, or sunrise_sunset. No sibling is named outright, so the routing is inferred rather than stated.

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