He Luo Li Shu Preview

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

Annotations only declare readOnlyHint=true, and the description reinforces that with an explicit no-persistence statement. It also discloses recovery behavior (inherits calendar, timezone, DST, true solar time and late-zi boundary from the bazi main chart) and a refusal path for four-pillar input, which is real behavioral context beyond the annotation.

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?

A single dense sentence whose clauses are all load-bearing: data source, computation method, refusal condition, exclusions. The wording is heavy with domain jargon but has no filler; the data-source constraint is front-loaded appropriately.

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?

For a tool with a nested oneOf subject, four additional parameters and no output schema, the description covers purpose and exclusions well but leaves the output form (only 'innate natal hexagram' is named) and three free-text parameters unexplained. An agent could invoke it with a valid subject but would be guessing about the optional fields and the response shape.

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 must carry the parameter burden. It clarifies only the subject union (profile vs. record_id) and the rejection of raw four pillars; notes, question, focus_area and the locale enum are never explained, so an agent cannot tell whether question/focus_area influence the computed hexagram or are just labels.

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 precise verb and resource: compute the Heluo Li Shu innate natal hexagram, and names the exact computational basis (Luoshu stem numbers, Hetu paired branch numbers, Lichun three-yuan palace lodging). It also draws an explicit boundary against siblings by declaring that yuan tang yao, post-heaven hexagram and fortune periods are not expanded, so an agent can tell it apart from preview_chenggu, preview_meihua and the bazi.* tools.

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 gives a hard input rule — subject must come from the user's profile or a chart record, and direct four-pillar input is rejected because the three-yuan year cannot be determined — which is genuine when-to-use guidance. However, it never names an alternative tool for the excluded features (yuan tang yao, post-heaven hexagram, fortune periods), leaving the routing to inference.

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