Tai Sui Relations

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

readOnlyHint=true already covers the safety profile, yet the description adds substantive computation semantics beyond annotations: the lunar-New-Year civil-midnight year boundary, the 1900–2100 domain, that time-of-day and timezone are ignored, that overlapping relations are all retained, and that no records are persisted. It does not describe the shape of the result, but the behavioral rules that determine the answer are well disclosed.

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 that front-loads the data source (subject birth date), then the comparison domain, then the disclaimers. Every clause carries information — year boundary, ignored time/timezone, retained overlaps, no persistence — with no filler. The run-on structure makes it slightly harder to scan than a split sentence would.

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 nested-subject tool with 6 parameters and no output schema, the description covers the essential input semantics and the relational outputs (值/冲/刑/害/破) but omits what the response actually contains and what question/focus_area/notes influence. Adequate to invoke correctly on the required fields, incomplete on the optional ones.

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 17% (essentially just target_year), so the description must compensate — and it partly does by explaining that subject resolves to either the current user's profile or a chart record's raw birth date, which is the key to the oneOf branching. It says nothing about locale, notes, question, or focus_area, leaving four of six parameters defined only by their names and types.

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?

States a specific computation: compare the subject's raw civil birth date against a target lunar year (1900–2100) for the 值/冲/刑/害/破 direct relations. It is clearly a Tai Sui relation lookup rather than a generic chart calculation. However, it never names the closest conceptual sibling, bazi.lookup_zodiac_branch_relations, so the boundary between the two is left for the agent to infer.

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?

Usage is implied by the scope language ('based on the current user's own profile or their chart record', 'target lunar year'), and the 'preview / no real-world advice / no records saved' phrasing signals a lightweight lookup rather than a full election. There is no explicit when-to-use, when-not-to-use, or alternative routing against bazi.lookup_zodiac_branch_relations or election.find_good_days.

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