Wealth Evidence

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

The annotation already declares readOnlyHint=true, so safety is covered; the description usefully adds that the output is evidence-only with no scoring or ranking and no inferential claims about occupation, risk, investment or region. Those negative-behavior disclosures materially shape how an agent should present the result. It does not say how the year window constrains output volume or what happens when the window is very wide.

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?

It is a single tightly packed sentence with no filler, and the positive scope is front-loaded ahead of the exclusions. The density of jargon in one unbroken clause chain makes it slower to parse than it needs to be, but nothing is redundant.

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?

The conceptual scope is covered well and the negative claims are explicit, which suits a read-only analysis tool. However, with 0% schema coverage, a oneOf on record_id/use_profile, and no output schema, the agent is left guessing both which identity parameter to supply and what shape the returned wealth evidence takes.

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 0%, so the description carries the full burden, and it only covers the year window ("调用方显式年份窗口"), leaving start_year/end_year order or limits unstated. Critically, the schema's oneOf requires either record_id or use_profile=true, but the description only speaks of "当前用户命盘" (the current user's chart), never explaining the record_id path or the profile fallback — a real ambiguity for invocation.

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 opening clause names a specific verb+resource: it assembles the natal chart's wealth-star (财星) revealed/hidden status, ten-god co-occurrence, chart structure and day-master strength, then lists luck-cycle/annual wealth-star triggers inside the caller's year window. That is clearly separable from siblings like bazi.analyze_entrepreneurship or bazi.calculate_luming. It stops short of a crisp one-line statement of the resource, since the reader must parse dense terminology to reach it.

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 the operating context (caller must supply an explicit year window) and sets topical exclusions — no scoring, no ranking, no occupation, risk-preference, investment or region inference — which tells the agent what this tool is not for. It never names an alternative sibling to use instead, so the routing guidance is implied rather than explicit.

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