Hour Pillar

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description adds genuinely non-obvious behavior: the Zi hour starts the day at 23:00 local time (a day-boundary rule that changes results for late-evening births) and the per-call cost. It does not state what invalid or ambiguous local times do – that detail lives only in the timezone parameter, not in the description.

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 substantive content is two tight sentences, front-loaded with the algorithm and then the boundary rule. The bracketed metadata lines (group, endpoint, required, cost) are boilerplate but each carries usable dispatch information, so the definition stays lean.

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 no explanation, and the annotations cover safety. What is missing is the domain linkage an agent needs to chain correctly – that the day stem drives the hour stem and therefore a day-pillar call may be a prerequisite – plus any hint about how the 23:00 boundary interacts with the timezone parameter.

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 only 40%: date, time, and language have no schema descriptions at all. The description partially compensates for `time` by explaining the 23:00 Zi-hour boundary, and the timezone/timezoneOffset semantics are already richly documented in the schema. `language` and the accepted date/time formats remain undocumented in both places, so the description neither fully compensates nor is redundant.

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?

It names a specific resource (the hour pillar) and the exact classical method (五鼠遁 / Five-Rats-Escape day-stem → hour-stem table), so an agent knows precisely what is computed. It does not, however, differentiate itself from the many BaZi siblings (astroway_bazi_four_pillars, astroway_bazi_month_pillar, astroway_bazi_chart), so a caller cannot tell from the text alone when this single-pillar call beats the aggregate chart call.

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 only implied: the pillar-scoping and the dependency on a day stem suggest it is the single-pillar primitive used when the full four-pillar chart is unnecessary. The metadata block supplies required inputs and cost (10 credits, Tier 1), which is useful operational context, but no explicit when/when-not or named alternative is given.

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