Flying Star natal chart (Xuan Kong Fei Xing)

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds two genuine behavioral facts beyond that: no server-side default for facing or period (the agent must supply both), and the composition of the returned chart. It does not say what happens if conflicting inputs are supplied (both degrees and mountain, both period and date), which is the main remaining ambiguity.

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: the first front-loads what the chart contains, the second tells the agent which parameters to send and in what alternate forms. No filler, and the critical 'Neither is defaulted' caveat lands at the end where it will be read as a constraint.

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 an output schema present the description needn't enumerate return values, and it still characterizes them usefully; annotations cover the safety profile. The gap is that a few of the 8 parameters (year, language, occupiedTime) get no mention anywhere, but the two parameters that actually drive the computation are fully explained.

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 13% (just timezoneOffset), so the description must carry the load, and it does: it maps 'facing' to degrees or 'facingMountain' to one of 24 mountains, and 'period' to either the 1-9 integer or 'occupiedDate' as the occupation date. That is the essential disambiguation for the core 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 deliverable — the nine-palace building chart with mountain/period/facing stars per sector, the named arrangement, and special patterns — which is a distinct resource from the sibling feng shui tools (annual_stars, bagua, kua, lucky_directions). An agent can identify both the subject (a building's natal chart) and the output content 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?

It gives solid guidance on input mode — face in degrees or as one of the 24 mountains, period directly or via occupation date — and warns 'Neither is defaulted', which affects how the call must be made. However it never names an alternative tool (e.g. annual_stars or lucky_directions) or states when this natal chart is the right choice over those siblings, so tool selection remains inferred.

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