标准六爻卦图

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers meaningful context: the image must be generated from the structure (“图片由结构生成”), with an explicit prohibition on AI redraw or manual assembly (“不得用 AI 生图重绘或手工拼爻线”), and the tool re-casts the hexagram itself. It does not cover delivery format of the PNG or failure modes, but the disclosed constraints are genuinely informative.

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?

Two dense sentences front-load the core function and enumeration of diagram contents, then cover generation constraint, sibling relationship, re-casting behavior, and the text fallback. Every clause earns its place; there is no filler or repetition of the schema.

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 10 parameters, no output schema, and no annotations, the description covers the core behavior and the text fallback well, but leaves gaps that matter for invocation: how the PNG is returned (path/URL/data URI), what valid values method/number accept, and the meaning of category. The cross-reference to liuyao_qimen_fusion partially fills this, but the definition is not self-sufficient for a fresh agent.

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 should compensate, but it only cross-references the sibling (“参数与 liuyao_qimen_fusion 一致”) rather than explaining the 10 parameters. The date/time fields are self-evident, but the required domain-specific parameters — method, numbers, category — get no value guidance and the schema offers no enums. The cross-reference is useful partial mitigation but the description cannot stand alone.

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 states a specific verb and resource: “直接画出固定坐标的 PNG 卦图” (directly draw a fixed-coordinate PNG hexagram diagram), and enumerates the exact contents (本卦、变卦、六亲、六神、世应、伏神、动爻). It also differentiates from the sibling liuyao_qimen_fusion by noting the parameters match but the output is the diagram plus text, leaving no ambiguity about what this tool produces.

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 explicitly frames this as the image companion to liuyao_qimen_fusion (“参数与 liuyao_qimen_fusion 一致，会重新起同一卦”), which tells the agent this tool re-casts the same hexagram rather than consuming a prior result, and it gives a concrete fallback condition (“宿主不能显示图片时就只用逐爻文字”). It lacks an explicit 'use X when you need interpretation, use this when you need an image' contrast, so the choice rule is implied rather than stated.

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