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

Annotations already declare readOnly/idempotent/non-destructive/finite-world, so the safety profile is covered. The description adds real behavioral depth beyond that: the 60-jiazi anchor (1990-01-01 = Bing-Yin) and the exact boundary rules — day/hour rolling at 23:00 local, year/month at Lichun and 節 instants — which are the edge cases that actually change results. It does not contradict the annotations.

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 dense sentences that front-load output scope, then methodology, then boundary behavior; the metadata footer is compact. No filler, though the astronomical caveats make the second sentence long.

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, and annotations cover safety. For a single-date computation tool the description supplies the key semantics (input shape, pillar scope, boundary rules). The one residual gap is that '23:00 local' is not tied explicitly to the timezone/timezoneOffset parameters.

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 57% (time, date, and language have no schema descriptions), so the description carries part of the load: it clarifies that `time` drives the hour pillar and that day/hour boundaries are 23:00 local. It adds nothing for `language` and only partially ties the 23:00 boundary to the timezone/timezoneOffset parameters.

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 concrete output ('All four pillars: year, month, day, hour') for a named resource, and the phrase 'All four pillars' implicitly contrasts with the sibling single-pillar tools (bazi_year_pillar, bazi_month_pillar, bazi_hour_pillar). An agent can distinguish it from the per-pillar siblings without opening the schema.

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?

'Pass `time` to compute the hour pillar' is a genuine conditional usage hint. However there is no explicit when-to-use statement versus alternatives such as astroway_bazi_chart or the individual pillar endpoints, and no stated exclusions. Usage is implied rather than spelled out.

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