14 Main Stars

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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts: it is a static reference table independent of date, plus the endpoint, required field and a 5-credit Tier ½ cost — cost and idempotence-by-nature are things an agent needs and the annotations don't convey.

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 core sentence is front-loaded and wastes nothing. The bracketed metadata block (group, endpoint, required, cost) is terse and skimmable, though it is boilerplate shared across the whole tool family rather than tailored here.

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 description still says what is returned (ordered stars with theme/archetype). What's missing is the rationale for requiring date/time/timezone on a date-invariant reference call, which leaves an agent unsure whether those values affect anything.

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 50%; timezone/timezoneOffset are documented in the schema and time is not. The description only restates '[Required: date]' and never resolves the oddity that a table which 'does not vary with the date' still requires a date — that is the one parameter question an agent will actually have.

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 resource and shape: the 14 main stars in canonical order (Zi Wei series then Tian Fu series) with theme/archetype. The clause 'Reference table: does not vary with the date' separates it from chart-producing siblings like astroway_ziwei_chart or astroway_ziwei_full_chart, though those siblings are never named.

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?

'Reference table: does not vary with the date' implies this is a static lookup rather than a per-chart computation, which is usable guidance. However it never explicitly says when to pick this over astroway_ziwei_full_chart or the palace tools, and it doesn't explain the lookup-vs-chart decision.

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