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

With no annotations, the description carries the full burden and does substantial work: determinism ('Same day → same answer'), access model ('Public · local · no API key'), a hard limit ('Max span 45 days') and a framing caveat ('Preview ≠ prediction'). It stops short of return format or error behavior, so not a 5.

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?

Dense but every fragment earns its place (determinism, triggers, outputs, access, limit, caveat). The front-load is slightly off—it opens on the 'rules engine' rather than the purpose—but it remains compact and scannable.

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 3-param, read-only, output-schema-less tool, the description covers purpose, triggers, outputs, limits and caveats adequately. Return-shape details are only lightly gestured at by 'lists dated L1 sky marks', but complexity is low enough that nothing essential is missing.

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 schema documents to/from/locale and their defaults. The description adds a genuinely param-relevant constraint not in the schema—the 45-day maximum span for the date range—plus intent framing for the locale output, exceeding the baseline 3.

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 names a specific resource—dated sky marks (new/full moon, eclipse, ingress, stations)—and a clear retrieval action, so an agent immediately knows the domain. It does not explicitly contrast with the nearest sibling (solar_terms also returns dated celestial events), which keeps it from a 5.

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?

Concrete bilingual trigger phrases ('新月哪天 / 日食哪天 / 接下来有没有逆行 / what sky events are coming') give clear when-to-call conditions. It also warns against fabricating 'pillars or fortune claims', but names no alternative siblings or when-not-to-use conditions.

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