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

With no annotations, the description carries the full burden and does disclose meaningful traits: deterministic output ('Same day → same answer'), scope (any civil date 1900–2100), and operational profile ('Public · local · no API key'). It does not cover error behavior or rate limits, but for a stateless lookup this is solid disclosure.

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 determinism statement is front-loaded, which is good, but the body is a dense run-on mixing trigger phrases, prohibitions, and meta-commentary ('Preview ≠ prediction'). The trigger list is defensible for routing, yet it repeats concepts and contradicts itself by listing 宜忌 as a trigger while disclaiming it.

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?

There is no output schema, so the description must explain returns, and its attempt is cryptic: 'body (sleep/load)' and 'plan (this month’s fold year + posture)' reference concepts that are not defined here. Date, hour, and locale are covered by the schema, but the return shape an agent should expect remains unclear.

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 100%, so date, hour, and locale are already fully documented in the schema, establishing a baseline of 3. The description only reinforces the date range ('Works for ANY civil date 1900–2100') without adding format or semantics beyond what the schema states.

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 states a specific resource and action: a date lookup that returns lunar + ganzhi pillars for any civil date 1900–2100. It also draws a boundary ('Do not read this as 宜忌 / lucky-day / 吉凶'), which helps separate it from fortune-telling tools. It never names a sibling tool, so differentiation from personal_day or today_rhythm is left to inference.

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?

The trigger list is unusually explicit ('Call when the user asks 黄历 / 老黄历 / 宜忌 / 黄道吉日 / ...'), giving concrete invocation conditions across zh and en phrasing. Negative guidance is also present ('Do not mention marriage, burial, or god directions'). However, it never routes the agent to an alternative sibling when a different need arises, and listing 宜忌 as a trigger while also saying not to read it as 宜忌 is internally confusing.

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