Star Ninja

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

Annotations already declare readOnlyHint=true, so safety is covered, yet the description still adds substantial behavioral context: the full set of returned fields, that darkness windows can be absent on some nights ("some nights have none"), and that both endpoints must be supplied as coordinates. It stops short of stating how many nights are forecast, units, or accuracy limits, which would be the remaining useful details.

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 the one-line purpose, then outputs, then usage triggers, then the coordinate constraint and exclusions. The longer enumeration of returned fields is justified because no output schema exists, and every clause carries distinct 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 carries the burden of describing returns and does so thoroughly, down to the "some nights have none" edge case. Combined with complete schema coverage and a read-only annotation, an agent has everything needed to call this correctly.

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 coverage is 100%, so the baseline is 3 and the schema already documents each coordinate and the optional nightDate. The description adds one genuinely useful constraint beyond the schema: "Both the start and the spot must be given as coordinates," clarifying no place-name input is accepted, and it frames nightDate as tied to the returned nights.

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 names a specific verb and resource with explicit scope: checking stargazing conditions at one spot over coming nights. It also enumerates the concrete outputs (darkness band, distance, drive time, map link, per-night cloud/moon data), so the agent knows exactly what the tool produces. No sibling tools exist, so no differentiation is needed.

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?

"Use it when someone asks where or when they can see stars, to check a place they name or compare several" gives explicit trigger conditions and both supported modes. The closing sentence states clear exclusions: it does not find, rank or recommend spots, or check access or safety. Nothing about when-not-to-use is left to inference.

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