Twenty-Eight Mansions

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

readOnlyHint=true already covers safety, and the description goes well beyond it: it names the underlying data source (a fixed day-branch + weekday index table), states the midnight date-change boundary, clarifies the tool is not an astronomical computation, denies that it derives activity verdicts, and confirms nothing is persisted. For a read-only lookup, these are exactly the behavioral traits an agent could 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?

Content is front-loaded: the verb and resource list come first, then the date contract, then the negative constraints. Every clause carries distinct information, but the whole definition is one dense semicolon-chained sentence, which makes it harder to parse than a short structured list would be.

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 usefully enumerates the fields returned (宿、吉凶、宿歌、七曜、动物、宫守), and the date contract is fully specified. The remaining gap is the unexplained optional parameters, which an agent could otherwise populate with wrong intent for this fixed-table tool.

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 40%, but the description compensates for the riskiest parameter by restating the date strictness and the no-time/no-timezone rule, and it explains that activity_type is thematic only and does not produce 宜忌 verdicts. However, three parameters (notes, locale, question) receive no explanation anywhere — schema or description — leaving their semantics opaque.

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 specific verb (查询) and a precisely enumerated resource set: 二十八宿、宿吉凶、宿歌、七曜、动物、宫守, all looked up from a lunar-go day-branch + weekday fixed table. It also distinguishes the tool from positional astrology by stating 不是真实月球位置, so an agent can tell it apart from siblings like astrology.calculate_chart without opening any schema.

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?

It gives explicit input preconditions (a strict YYYY-MM-DD Beijing civil date in 0001–9999, midnight day rollover, no time-of-day or timezone) and three explicit exclusions: not a real lunar position, no activity conclusions derived from a single mansion, and no records saved. It stops short of naming an alternative sibling for event suitability (e.g. election.find_good_days), so routing is implied rather than stated.

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