Generate Chinese Year Forecast (PDF or HTML)

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses the key behavioral traits: `pdf` stores a file and returns a url while `html`/`markdown` are self-contained and unstored, pricing is identical across formats, and the call is premium-priced enough to warrant user confirmation. That is exactly the context an agent needs before spending credits, and nothing conflicts with the annotation set.

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 purpose is front-loaded and the content enumeration, while delivered as one dense sentence, genuinely tells the caller what the deliverable contains. The trailing metadata (group, endpoint, required field, cost) is terse and earns its place; only the long section list could be tightened given an output schema exists.

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 need not explain return values, and it covers what remains: format storage behavior, pricing, defaults, and the data sources behind the calculation. For a premium 9-parameter report endpoint, an agent can invoke it correctly from this text.

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 67%, so the schema carries much of the load, but the description ties parameters to output meaning: `date` is the birth date that fixes the animal/element, `time` matters when birth is near a Lichun boundary, and `year` defaults to the next calendar year. It adds genuine semantic linkage rather than repeating field text.

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 a specific artifact (Chinese zodiac year forecast) and enumerates its contents — natal animal/element, year pillar with Lichun dates, branch relation (本命年, 冲太岁, harmony, trine, harm), allies/opposites, and the twelve solar months. It also distinguishes itself from the sibling calculators by stating that the animal comes from /chinese/zodiac/animal and boundaries from the ephemeris, so an agent can tell it apart from astroway_chinese_zodiac_animal or astroway_bazi_year_pillar.

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 cost line gives real decision guidance — 5,000 credits at Tier 7, ~50% of a free monthly budget, confirm with the user first — which steers an agent toward asking before calling. However, there is no explicit statement of when to pick this report over the narrative report siblings or the standalone zodiac/baZi tools; that routing is left to inference.

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