Chenggu Bone Weight

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 true-solar-time or DST re-correction, no persistence ('不保存记录'), and a frozen/canonical verse mapping rather than a generated one. These are exactly the non-obvious traits an agent needs. It still says nothing about output shape or failure behavior when the record lacks a verifiable civil birth date.

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?

There is no filler and the input basis is front-loaded, but the whole definition is one long semicolon-chained sentence mixing input requirements, calendar edge cases, and output semantics. An agent must parse it as a run-on rather than scanning discrete clauses.

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 read-only, no-output-schema tool with a nested subject object, the description covers the algorithm and the calendar edge cases (late zi hour, leap-month halves) well. But with no output schema and four undocumented optional parameters, an agent still does not know what the result contains or how question/focus_area/locale affect the call.

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 only 20% across five parameters, so the description needs to compensate. It reinforces the subject constraint (profile vs. record_id, and that four-pillar-only records are unusable), but that constraint is already spelled out in the subject schema description. The roles of question, focus_area, notes, and locale are left entirely undocumented in both places.

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 concrete computation: look up four table weights from the lunar year/month/day/hour, sum them, and match a frozen verse by gender ('四项查表相加后按命主性别匹配冻结歌诀'). Combined with the tool name, an agent can tell this apart from the other divination.preview_* siblings. It never uses the term 称骨/bone weight explicitly, relying on the name for that framing.

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 states the input precondition clearly ('基于当前用户本人资料或其命盘记录'), which implicitly tells the agent when this tool is applicable and that a raw four-pillar record is not. However, it gives no guidance on when to pick chenggu over preview_liuyao, preview_meihua, or the other divination siblings, and no exclusions beyond the subject source.

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