Wu Tu Solar Election

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

Annotations only supply readOnlyHint, so the description carries most of the load and does add real behavior: the zi hour is split into the 00 and 23 segments of the supplied civil date with separate trace records, later windows do not wrap back to already-passed dates in the month, and nothing is persisted. The one gap is that the shape of the returned chart is not characterized at all.

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?

It is a single dense semicolon-chained sentence with the core computation front-loaded, which is efficient, but the clauses on zi-hour segmentation and window non-wrapping are packed in with equal weight and are hard to separate on a first read. No filler, but the structure could be broken into distinct statements.

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 preview with no output schema and five parameters, the description covers scope, the calendar convention, the zi-hour edge case, the no-suitability caveat and non-persistence — enough to invoke correctly. It stops short of describing the returned chart's structure and leaves three optional parameters unexplained.

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 40%, so the description must compensate, and it partially does by tying the date to Beijing-time civil reckoning and by reiterating that activity_type is only an interpretive theme rather than a suitability input. The notes, locale and question parameters receive no explanation anywhere, and the zi-hour 00/23 segmentation is the only genuinely new parameter-level insight.

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 computation (值日 plus a complete twelve-shichen nine-star chart) and names the rule set it applies (月朔截法, 排山九星), so an agent knows exactly what this tool produces. It does not explicitly contrast itself with the sibling election previews (preview_taisui, preview_jianchu, preview_xiu, preview_donggong), so the 'wu tu' system boundary is only implicit in the title.

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 includes a useful negative cue — the internal layer does not judge suitability of specific matters — which implies the agent should look elsewhere for activity selection, but no alternative tool is named. There is no positive statement of when this preview should be chosen over the other election.* previews; usage must be inferred from the rule names.

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