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

Annotations already cover read-only, idempotent, open-world, non-destructive safety. The description adds genuinely useful behavior beyond that: stale feeds yield status=null with unavailableReason rather than a false 'clear', and results carry source/freshness metadata. It does not cover rate limits or pagination, but for a read tool the stale/never-false-clear disclosure is the key risk-relevant detail.

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 return-value content is well front-loaded, but the bulk of the text is a wall of unrelated interpretation rules about tides, model sea height, paddleboard drift, kitesurfing activity keys and launch access. Those sentences do not help an agent select or invoke get_lightning and materially dilute an otherwise focused definition.

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 must describe returns, and it does: field-by-field for the point mode, a status-per-spot summary for the no-coordinate mode, plus freshness metadata and the null/unavailableReason contract. It is close to complete for invocation purposes; only the exact shape of the per-spot response is left thin.

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 single query object with optional lat/lon has 0% schema description coverage per the signals, so the description carries the load. It explains the semantic branch clearly ('With lat+lon: ... Without lat/lon: status per spot'), which tells the agent that omitting coordinates is a valid, different mode rather than an error.

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 (GOES-19 GLM lightning status) and enumerates exactly what is returned for each mode (level, nearest strike distance/time, strikes in 15 min, all-clear time, SPC outlook, last 30 min of flashes). It also distinguishes itself from the sibling list_spots for named-spot coordinates, so an agent can route without opening schemas.

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 two operating modes are explicit (with lat+lon vs without, per-spot), and it names the alternative for named locations ('Prefer list_spots for named spot coordinates'). It also routes kitesurfing questions to get_conditions, though that guidance is about adjacent concerns rather than when to call this tool versus its lightning-relevant peers.

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