bazi_chart八字排盘 from birth date and hour: four pillars (年月日时柱), five-element counts, 纳音, zodiac. Uses true solar-term boundaries.
| Name | Required | Description | Default |
|---|---|---|---|
| datetime | Yes | Birth datetime YYYY-MM-DDTHH:mm |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds a useful behavioral detail by noting that it uses true solar-term boundaries, which affects chart accuracy, and enumerates output elements. This is beyond the annotation-provided safety profile, making it transparent for expected behavior.
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 two short sentences, front-loads the main function, and packs relevant details (output components and the solar-term boundary method) without redundancy. Every phrase adds value, making it well-structured and concise.
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?
Given the tool has one parameter, complete schema documentation, explicit annotations, and an output schema, the description covers the essential context: input, purpose, and distinctive calculation logic. It does not need to explain return values, as the output schema handles that. The only minor gap is timezone handling, but that is not essential for a straightforward birth datetime input.
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?
The schema fully documents the only required parameter (datetime) with format YYYY-MM-DDTHH:mm, providing 100% coverage. The description simply refers to 'birth date and hour' without adding new parameter semantics, so the baseline of 3 is appropriate.
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 clearly states the tool computes a BaZi (Four Pillars) chart from birth date and hour, listing key output components (four pillars, five-element counts, 纳音, zodiac). This differentiates it from sibling tools like lunar_calendar or huangli, which serve different purposes. The verb '排盘' (chart calculation) is specific and resource-oriented.
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 implies the tool is for generating BaZi charts from birth datetime, giving clear context for when to invoke it. However, it does not explicitly name alternatives or exclusion criteria, so it stops short of providing full when/not guidance. It still qualifies as clear context with no exclusions, meriting a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly distinct: bazi_chart, lunar_calendar, huangli, pick_lucky_days all relate to Chinese calendrical/astrological concepts but have different purposes (birth chart, lunar info, almanac, lucky day selection). However, bazi_chart and lunar_calendar both touch on 干支/zodiac; pick_lucky_days could overlap with huangli. Minor ambiguity, but descriptions clarify.
Tool names are all snake_case and mostly descriptive, but they don't follow a strong verb_noun pattern (e.g., pick_lucky_days is verb+noun, but bazi_chart and phone_info are noun-like). Slight inconsistency in style, but the pattern is predictable enough.
10 tools is well-scoped for a China-focused utility server. Each tool serves a distinct purpose (ID validation, phone info, holidays, calendar, pinyin, network reachability), and the count feels reasonable without being bloated or thin.
The server covers a broad range of China-specific utilities, but there are gaps: no tool for Chinese address parsing, no tool for bank card validation, no tool for translation. While the existing set covers common needs, the 'china' theme could benefit from more coverage. Also, what_can_you_do suggests recipes but the actual tool set lacks some common use cases.