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

With no annotations, the description carries the full burden and does substantial work: determinism ('Same day → same answer'), an anti-hallucination constraint ('Do not invent pillars or fortune claims'), a hard auth requirement (BALANCE_API_KEY + birth profile), and a named error ('personal_timetable_requires_key') with a recovery path. It omits rate limits, latency, and any output 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?

Dense and reasonably front-loaded: determinism and the never-invent rule come first, trigger phrases next, then auth/error handling. The fragment list 'dated sky, sandbox assumptions, fold-memory prompts' is opaque jargon that consumes space without conveying an actionable fact.

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?

Auth, error handling, and determinism are well covered for a zero-annotation tool with a nested birth object. However, with no output schema, the description should convey what the response contains, and instead offers vague fragments ('dated sky, fold-memory prompts') that don't tell an agent what it will receive or how to present it.

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 the schema already documents date, month, locale, and the nested birth object including the gender/dayun rationale. The description only adds that a birth profile is required in practice despite the schema marking it optional, which is marginally useful but below the schema's own level of detail.

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?

States a specific resource and mechanism: a personalized flow-month computed as day-master vs month stem from a deterministic rules engine. It also draws a boundary ('Not a fortune verdict'), which helps an agent distinguish it from a generic horoscope tool, though it never names the sibling it differs from (personal_day, month_brief).

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?

Gives concrete invocation triggers in both languages ('我这个月怎么样 / 我哪周该推进 / my month') and an explicit when-not path (empty key → use free tools instead). It stops short of naming the specific sibling tools to fall back to, leaving the alternative as 'free tools' generically.

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