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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description need not repeat safety. It adds valuable behavioral detail: time is 'a single evaluation instant, not a window,' results are ranked 'brightest-and-highest first,' sky gating is based on Sun's altitude, and default elevation/min_altitude semantics are explained. The geocoding limitation is also disclosed. No contradiction with annotations.

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 a bit long but well-organized: the opening sentence delivers the core purpose, followed by process, time semantics, elevation guidance, and a geocoding caveat. It is front-loaded with the most important information and each sentence earns its place by either clarifying semantics or giving usage direction. Slightly more verbose than necessary, but structure compensates.

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 tool with 7 parameters and an output schema, the description covers everything an agent needs to invoke it correctly: the evaluation procedure, the meaning of `time` as a single instant, how to handle 'tonight,' default elevation, min_altitude for horizon filtering, include_stars behavior, and the upstream geocoding requirement. The output schema handles return details. Nothing essential is left unstated.

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 parameters are already documented. The description enriches semantics beyond the schema: it clarifies that `time` must be a single instant and suggests using it after astronomical dusk for 'tonight' queries, and it explains that `min_altitude` is for skipping horizon-grazing objects. This adds decision-relevant context not present in the raw schema field descriptions.

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 opens with a crisp one-line purpose: 'The one-call “what is up right now” answer,' then details the algorithm (iterate bodies, compute altitude/azimuth, filter above horizon, rank brightest-and-highest). It clearly distinguishes itself from sibling tools like astronomy_get_ephemeris or astronomy_get_rise_set by focusing on the aggregate visible-sky snapshot. The verb (list) and resource (visible bodies) are explicit.

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 concrete usage context: for 'tonight,' it instructs to pass a time after astronomical dusk and points to astronomy_get_rise_set on the Sun as the way to find that time. It also notes the server does not geocode, advising to resolve coordinates upstream. While it doesn't enumerate every alternative tool, it implicitly separates this from ephemeris/rise-set tools by framing it as the quick sky summary.

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