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

Annotations already declare read-only, idempotent, closed-world, so the bar is lower, yet the description still adds substantive behavior: historical time zone and true-solar day boundaries, 3-days-per-year luck calculation with yang/yin direction rules, pillar comparison against solar terms, and the 1801–2099 supported range. It stops short of describing error payloads or output shape, keeping it at a strong 4.

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?

Front-loaded with purpose and outputs before diving into parameter mechanics, and nearly every clause carries operational information. Minor waste: the trailing bilingual restatement of the Gregorian range (公历日期范围…) duplicates the preceding English sentence.

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 13-parameter, nested-object, no-output-schema tool, the description covers time-zone handling, supported date range, boundary-resolution behavior, and which facts are returned. It does not sketch the response structure at all, which matters somewhat given there is no output schema, but the enumerated deliverables largely compensate.

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 85%, so baseline is 3, but the description adds meaning the schema does not: focusDate is evaluated at noon against the birth place, detailYears is capped at ten inclusive years and must fit the pre-luck/twelve-cycle timeline, and ranges follow Lichun-through-Xiaohan month boundaries. Calendar/leap-month and boundaryChoices semantics are largely left to the schema.

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?

Opens with a specific verb+resource ("Calculate a full Bazi chart using the Xiaodao engine") and enumerates the concrete outputs: four pillars, lunar date, auxiliary palaces, luck start/direction, twelve cycles, and focused period facts. That level of specificity clearly separates it from siblings like qimen_chart and true_solar_time.

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?

Gives real operating guidance: focusDate selects a noon local civil date, detailYears adds up to ten inclusive years, allDaysOfMonth expands the solar-term month, and repeated/nonexistent times return needs_input or are not calculated. It also sets expectations with "returns chart facts, not an interpretation." It does not explicitly route between this and qimen_chart, so not a 5.

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