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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), but the description adds valuable behavioral context: units, null handling, timestamp/source status, visibility type, and current sign convention. It goes well beyond the annotations and is especially useful because there is no output schema, though it still does not enumerate all returned fields.

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 appropriately short and front-loads the core purpose before moving to output details and units. The final sentence 'Returns data and source/freshness metadata' partially repeats the earlier source/timestamp point, so it is not perfectly tight, but overall it is efficient.

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?

For a no-output-schema tool, the description does a fair job describing return shape, units, and null behavior. However, it leaves significant invocation gaps: no guidance on choosing this over sibling forecast tools and no explanation of the nested query parameters, so an agent still relies heavily on the input schema.

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 0%, so the description must compensate, but it barely does. It implies a 'verified spot' and an hours horizon, yet it provides no spot format, no mention of the default 24 hours, and no constraint details such as the 1–168 hour range.

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 resource and forecast horizon: 'Thunderstorm forecast for a verified spot over the next hours.' That is clear enough to distinguish a thunderstorm forecast from a generic forecast, but it does not explicitly name alternatives such as get_forecast or get_lightning, so it stops short of full sibling differentiation.

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 gives no explicit when-to-use or when-not-to-use guidance relative to the many sibling forecast and hazard tools. 'For a verified spot over the next hours' implies a context but does not route the agent between this tool and get_forecast, get_lightning, or get_marine_alerts.

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