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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile needs no restating. The description adds genuinely useful domain behavior: the day opens at the Zi hour at 23:00 local time, which materially affects which hour pillar is returned and is not derivable from the annotations or schema. Cost tier is also disclosed. It stops short of stating the input source (birth date/time/location) or output shape, but the output schema covers the latter.

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 and tight: the operative sentence comes first and the Group/Cost tags are compact metadata rather than filler. The untranslated 五鼠遁 term is slightly opaque for a non-specialist but is followed by an English gloss, so no meaning is lost.

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?

An output schema exists, so return values need not be described. For a specialized BaZi sub-tool buried among hundreds of siblings, however, the definition omits the minimal context an agent needs to select it: what the Hour pillar represents, how it differs from the sibling pillar tools, and what inputs it draws on. Adequate but with clear gaps.

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?

With 7 parameters and 57% schema description coverage, the schema already documents the tricky ones (timezone, timezoneOffset, precision, fields). The description adds no parameter-level detail and never clarifies the required date/time formats (patterns only) or the language field, which the schema leaves bare. The mention of 23:00 'local time' loosely signals the timezone parameter's relevance, so it is not a total wash, but it does not compensate for the coverage gap.

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 verb+resource: it derives the Hour pillar using the 五鼠遁 day-stem-to-hour-stem table, and clarifies the Zi-hour day boundary. That is more precise than a tautology. It does not, however, distinguish itself from closely-named siblings like astroway_bazi_four_pillars, astroway_bazi_year_pillar or astroway_bazi_chart, so the agent must infer the distinction from the name alone.

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?

There is no guidance on when to reach for this tool versus the other BaZi pillar tools or the aggregate bazi_four_pillars/bazi_chart. No prerequisites, exclusions, or alternatives are named. The Group and Cost tags give taxonomy and price but not usage conditions.

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