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

Annotations already state readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context — equal-weight per-period cell statistics rather than area-weighted, and that oversized results are staged with previews, counts, and SQL handles queried via summaryDataset in summaryIndex order. That is useful but stops short of stating limits, quotas, or how large a request must be before staging kicks in.

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?

Every sentence carries a constraint or routing rule, and the core purpose is front-loaded. It is dense to the point of being a single block, and phrases such as 'summaryDataset in summaryIndex order' assume reference knowledge rather than being self-contained.

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?

Given three oneOf variants, an output schema, and 100% schema coverage, the description supplies exactly what structured fields cannot: region-size limits, antimeridian handling, staged-result workflow, and the statistical semantics of the returned cells. An agent can call this correctly without further documentation.

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 the baseline is 3, but the description adds constraints the schema does not encode: the 2–10 degree span per axis, single-parameter restriction, and the prohibition on year fields for climatology. It leaves canvas_id, units, timeStandard, and community entirely to the schema, which is acceptable given their documentation.

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 first sentence gives a specific verb (retrieve), resource (one parameter over latitude/longitude bounds), and hard scope limits (2–10 degrees per axis, single parameter, three temporal resolutions). It immediately separates the tool from point-based siblings by describing region bounds and by naming nasa_power_get_climatology as the point alternative.

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?

Explicit routing rules are present: use nasa_power_get_climatology for custom years at a point, split antimeridian regions into separate calls, and note that regional climatology takes no year fields. These are concrete when/when-not conditions an agent can act on without opening another schema.

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