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

Annotations cover readOnly/idempotent/openWorld, yet the description adds much more: 5-minute caching, `stale: true` fallback on SWPC outage, 503 upstream_unavailable semantics (uncharged, retry later), latency expectations, price, and the free-tier pool shared across all skypeek routes. It also warns that quoted report/alert text must be treated as data, not instructions — a real prompt-injection safeguard.

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?

Long but dense: purpose is front-loaded, then input, provenance/licensing, caching, error behavior, latency, and pricing. Almost every sentence carries operational value; the licensing/endorsement clause is the one mild padding item for an agent audience.

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 carries the burden of describing return values and does so thoroughly (fields, freshness, stale flag, alert count). Combined with the error/rate-limit/pricing context, an agent has everything needed to call and interpret this tool.

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?

Zero parameters, so the baseline is 4. The description reinforces this by stating an empty object is expected, leaving no ambiguity about how to invoke it.

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+resource and enumerates exactly what is returned: Kp index with G-scale, 3-hour-step Kp forecast, solar wind speed and Bz/Bt, and up to 10 recent SWPC alerts. This clearly distinguishes it from siblings like aurora_forecast, get_weather, and sun_moon_times.

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?

Explicitly says 'Input: nothing (send an empty object)', giving the agent a clear calling context, and the data scope implies when this is the right tool. It does not, however, name alternatives (e.g. aurora_forecast for visibility rather than raw indices) or state when NOT to use it.

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