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

Annotations already cover the safety profile (readOnlyHint, idempotentHint), yet the description still adds real behavioral detail: a window of consecutive days starting at standard_time, per-day suitability conclusions with 判定依据 when event is supplied, and the important guarantee that an empty result within the range is not an error. The only gap is that it does not discuss pagination or result-size limits beyond count, but the output schema carries return shape.

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?

Everything is front-loaded: purpose first, then trigger conditions, then return behavior, then the exclusion. It is dense and uses semicolons to pack several clauses, which slightly hurts scannability, but no sentence is filler.

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?

Given three required parameters, an output schema, and read-only/idempotent annotations, the description covers everything an agent needs: when to call, when to route elsewhere, how the date window is formed, and the no-match behavior. Enum values and the 1–30 count bound are already documented in the schema, so no repetition is required.

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 100%, so the baseline is 3, but the description adds relational meaning the schema cannot: standard_time and count jointly define a consecutive-day window beginning at the given date, and event changes the response by attaching a per-day conclusion and its rationale. That goes beyond restating the individual field docs.

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 opens with a specific verb and resource in Chinese, namely 黄历择日查日 (querying almanac days for date selection), and immediately clarifies the scope as almanac auspiciousness facts rather than astrological charting. It explicitly names what the tool is not (八字/紫微 natal and annual charts), which lets an agent distinguish it from the large set of sibling charting tools without opening any 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 states concrete triggering user intents: asking for suitable/inauspicious dates for an event, whether a given day is auspicious, or almanac 宜忌 facts. It also gives an explicit exclusion: 命理合参 involving 八字/紫微 natal or annual cycles must use the corresponding chart and query tools instead. This is a clear when/when-not split with a named alternative category.

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