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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world call, so the safety profile is covered. The description adds genuinely useful operational context the annotations lack: credit cost (5 credits, Tier ½) and the required 'date' input. It still says nothing about latency, range limits on dates, or what the palace output represents.

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 one-line meaning is front-loaded, which is good, but the bracketed metadata block (group, endpoint, cost) is template boilerplate rather than prose; the endpoint URL in particular duplicates what the agent already has. Nothing is wasted exactly, but the structure is machine-stamped rather than purposeful.

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. However, for a 6-parameter computation the description never says whose chart is being computed, that 'date' should be a birth date, or how this palace relates to astroway_ziwei_full_chart or the other palace endpoints. An agent has enough to fire the call but not enough to know it is choosing the right one.

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 67%, with the four optional parameters (fields, timezone, precision, timezoneOffset) richly documented in the schema itself. The description only restates '[Required: date]' and adds no semantics for 'date' or 'time', which are the two undocumented parameters. Baseline 3 for a schema that already does most of the work.

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 is a bare noun fragment, 'Profession, status, official position,' with no verb stating what the tool does or returns. The name and title ('Career Palace (Guanlu)') carry most of the meaning, and the fragment at least narrows the topic to career significations within Zi Wei Dou Shu. It does not distinguish this palace endpoint from the nine sibling palace endpoints beyond that topical hint.

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, no mention of when this palace is preferred over astroway_ziwei_palace_destiny or astroway_ziwei_twelve_palaces, and no prerequisites. The only actionable hints are the metadata brackets ('[Required: date]', '[Endpoint: POST /v1/ziwei/palace-career]'), which are invocation facts 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.