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

Annotations already cover read-only, idempotent, open-world, and non-destructive traits, so the description is free to add what they cannot: the upstream source (NOAA GOES-East), a hard staleness window (last 15 minutes), and a geographic restriction (US only). It does not disclose behavior when no strikes exist or when the point falls outside satellite coverage, which is the remaining behavioral gap.

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?

Front-loaded with resource, source and time window, then the return contents, then the usage trigger — a sensible information order with no filler sentences. Slightly long and chatty in the quoted example, but every clause carries real information.

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 correctly carries the return-value burden and does so thoroughly, including units, directions and the derived 30-minute clock. The gap is that with zero required parameters it never says what the tool does when called with no location at all, nor how it behaves with no strikes in range.

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%, so lat, lon and place are already documented and the baseline is 3. The description adds nothing about the parameters — notably it does not explain the lat/lon vs. place fallback or what happens when all three optional params are omitted.

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 resource (nearest lightning strikes) with concrete scope (right now, last 15 minutes, US, NOAA GOES-East) and enumerates what is returned: distance/direction/age, counts within 10 and 30 miles, and the 30-minute rule clock. The only weakness is that it never names the closest sibling, storm_watch, so an agent must infer the real-time-vs-forecast split itself.

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?

Gives clear situational triggers — on the water, at a ballgame, beach, campsite, or when asked about storms/lightning — which is strong positive guidance. It stops short of explicit exclusions (e.g., 'not for multi-day forecasts, use storm_watch') or prerequisites, so the when-not side is missing.

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