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

Annotations already establish readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful operational context the annotations do not carry: the endpoint, the cost (5 credits, Tier ½), and the single required parameter. It still says nothing about whether the result is computed per-birth-data or a static catalog, which is the main behavioral question here.

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 content sentence is front-loaded and the bracketed metadata is scannable, with essentially no wasted prose. The cost/tier/endpoint block is boilerplate but compact and informative, so structure is good even if the payload sentence is thin.

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 explained, but for a chart-derived list sat among a dozen near-name-identical ziwei tools the description leaves the agent without scope or routing information. It never clarifies the relationship to astroway_ziwei_chart or the palace-specific endpoints, nor whether a birth time is needed to produce meaningful results.

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?

Six parameters at 67% schema description coverage, and the description contributes only 'Required: date'. It adds no meaning about 'time' (does the palace layout depend on hour of birth?), 'timezone', or the compact-mode 'fields'/'precision' options beyond what the schema already documents. It does not compensate for the undocumented date/time 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?

The description names the resource and its payload ('All 12 palaces with English/pinyin/Chinese names + theme + rules'), which is more than a tautology, but it uses no verb (list/fetch/compute) and never distinguishes itself from the many overlapping ziwei siblings such as astroway_ziwei_chart, astroway_ziwei_full_chart, or the individual astroway_ziwei_palace_* tools. An agent cannot tell from this text alone why it would call this instead of the full chart.

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?

There is no when-to-use guidance at all: no prerequisites, no exclusions, and no named alternatives among the ~12 ziwei siblings. The bracketed '[Required: date]' and '[Cost: 5 credits]' lines are metadata about invocation cost, not about tool selection.

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