observing_sheet

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

With no annotations and no output schema, the description carries the full burden and does deliver real behavioral facts: omitting place is an error, lat/lon is an accepted alternative, and band="infrared" is readable at night while visible is dark. It stops short of describing the returned artifact itself (image vs. structured fields), how the judgment is classified, or any latency/caching behavior, and the closing link instruction is unexplained.

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 one-line purpose is front-loaded, followed by usage examples and then a compact Args block — a sensible ordering. The trailing instruction about presenting the returned link is useful but sits orphaned at the end, disconnected from any explanation of what the link is.

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 four-parameter tool with no annotations and no output schema, the description covers purpose, all parameters, the key default, and the required-input failure mode. The remaining gap is the return contract — that it is an image/link artifact the agent should surface — which is only hinted at by the final sentence.

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, and it largely does: place is documented with an example and an explicit error-if-omitted rule, lat/lon get valid ranges and the pairing constraint, and band gets both a default and a rationale. It goes meaningfully beyond the bare string-typed schema and even corrects the misleading required-parameters count.

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?

"天体観測の判断シート（判定＋雲量＋衛星＋雨雲）を1枚で返す" names a specific resource and enumerates exactly what the single sheet contains, so an agent knows this is a composite observation-decision image, not a raw data query. It does not explicitly contrast with the closest siblings (astronomy_weather, weather_satellite_now, sky_map_with_satellites), so differentiation is left implicit.

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 example utterances ("今夜の観測は大丈夫? 図で", "雲の様子と雨雲を1枚で見せて") imply the use case well. However, there is no explicit statement of when NOT to use it versus astronomy_weather or weather_satellite_now, and no prerequisites beyond the place requirement.

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