Da Liu Ren Preview

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

Beyond the readOnlyHint annotation, it discloses a strong set of negative behaviors that matter for downstream interpretation: it never reads the server clock, never fabricates 年命/行年/神煞/课体附格, never asserts an event outcome, and never persists a record. These exclusions directly prevent an agent from hallucinating components the tool does not compute.

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 content is packed into a single semicolon-chained sentence that front-loads the casting action before the computation list and then the exclusions, so ordering is sensible. It is dense and would read more easily split into mode description versus limitation clauses, but no clause 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?

With no output schema, the description usefully enumerates what a call returns (plates, four lessons, three transmissions, generals, xun-kong, six relatives, strength), which is exactly the missing piece. The remaining gap is coverage of the optional context parameters (subject profile, locale, question framing), which the schema only partially documents.

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?

At 54% schema coverage the description should compensate, and it does clarify the two-mode split plus the critical date_time semantics (caller-frozen, 1800-2100, Beijing civil time, no timezone). But it is silent on question, notes, locale, time_hint, focus_area, subject.record_id vs use_profile, and on month_branch driving the 旺衰 calculation — the schema must carry all of that on its own.

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 verb (起课/计算) and a specific resource (大六壬天地盘、四课三传、十二天将、旬遁旬空、六亲与旺衰), enumerating the exact artifacts produced. The resource name '大六壬' alone distinguishes it from sibling divination tools such as preview_liuyao, preview_meihua, preview_qimen, so an agent can select it without opening the 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 clearly states the two supported invocation paths — caller-frozen datetime casting versus manual chart-correction fields — and thereby tells the agent which mode to pick given available inputs. It does not, however, compare itself to other divination methods or state when an agent should prefer another system, so routing guidance beyond mode selection is absent.

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