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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds genuinely behavioral content beyond that: the explicit day-boundary convention that the Zi hour opens the day at 23:00 local time, which changes computed results at the day edge. It stops short of error behavior or what happens with ambiguous/skipped local times.

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?

Two tight sentences front-loading the method and the boundary rule, followed by a compact bracketed metadata block. The 'Required: date, time' line duplicates the schema's required array, which is the only real waste; group, endpoint and credit cost are non-redundant and useful.

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?

With 7 parameters, an output schema and full annotations, the main remaining gap is orienting the agent on time input: an hour pillar is only well defined once the local-hour convention and the timezone/timezoneOffset choice are resolved, and the description only alludes to 'local time' without saying which parameter governs it. Return values need not be explained since an output schema exists. Adequate but not complete for a time-sensitive calculation tool.

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 57%, in the middle band. The description only echoes the required list ('Required: date, time'), which the schema already encodes, and adds nothing about how timezone or timezoneOffset interact with the hour boundary — arguably the most consequential semantic for an hour-pillar tool. The richer timezone, timezoneOffset, fields and precision semantics are all carried by the schema, so a baseline 3 is appropriate.

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 and its algorithm: the hour pillar derived via the 五鼠遁 (Five-Rats-Escape) day-stem → hour-stem table, plus the Zi-hour day boundary rule. That is far more specific than the bare name 'Hour Pillar'. It never names or contrasts the obvious siblings (astroway_bazi_year_pillar, astroway_bazi_month_pillar, astroway_bazi_four_pillars), so sibling differentiation is left to inference.

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?

No when-to-use guidance at all. The description does not say to prefer this over astroway_bazi_four_pillars when all four pillars are wanted, nor when a standalone hour pillar is appropriate, nor what date/time combination is meaningful. The only procedural hints are the metadata lines (endpoint, required params, cost), which are call mechanics rather than usage guidance.

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