Xiao Liu Ren Preview

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

Annotations only declare readOnlyHint=true; the description adds real behavioral context on top: no records are persisted (不保存记录), datetime input is treated as local civil clock time with no timezone offset, the 23:00 子时 boundary does not roll the day forward, and leap months reuse the same-named month number. These are exactly the non-obvious rules an agent would otherwise get wrong.

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?

A single dense sentence, but the core method is front-loaded and every clause carries a distinct rule (method, lunar conversion, day boundary, leap month, no persistence). No filler, though the semicolon-chained structure makes it slightly hard to scan.

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 an 11-parameter tool with a nested subject object and no output schema, the description covers the calculation and the two timing rules but says little about what is actually returned beyond '通行断诀' — no indication of palace, verse structure, or whether locale changes output language. Adequate but with clear gaps.

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 only 45% across 11 parameters, so the description needs to carry weight; it does explain casting_time's no-offset clock format, the 23:00 rule, and leap-month input for month_number. However, question, focus_area, time_hint, notes, locale, and the subject use_profile/record_id exclusivity get no mention in the description (the subject schema does self-document). Partial compensation only.

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 states a specific verb and resource: it computes the landing palace via the six-palace sequential method (大安起正月、月上起日、日上起时) and returns the standard interpretation verse (通行断诀). Naming the 小六壬 palace method separates it from sibling divination previews such as preview_liuyao or preview_meihua, though it never explicitly contrasts itself with them.

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?

There is no statement of when to pick this tool over the many sibling divination previews, nor which casting_method (manual vs datetime) an agent should choose and under what conditions. The mode-specific behavior is described, but only as mechanics, not as selection guidance.

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