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

Beyond the readOnlyHint annotation, the description explains important behavioral details: chart facts are computed server-side, the narrative is an AI-labeled bubble, and the assistant should only add brief text after the card renders. This adds meaningful behavioral context without contradicting the safe read-only annotations.

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 description is compact and front-loaded: purpose in sentence one, card contents in sentence two, and behavior/interaction guidance in sentence three. Every sentence earns its place; no filler or redundant restating of the title.

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 complex nested birth object and an output schema, the description is largely complete: it identifies the user need, the rendering surface, the narrative ownership, and the post-call behavior. One minor gap is that it does not address prerequisites or fallback behavior if the prior legend_saju_read_fortune call is absent.

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?

Top-level schema description coverage is 0%, so the tool description should compensate for the birth and narrative parameters. It partially does: it tells the model to write narrative/headline fields grounded in a prior read_fortune call and that chart facts are server-computed. But it doesn't add detail on birth semantics or the relationship among birth fields beyond what the nested schema already provides.

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 opens with a precise action and resource boundary: 'Render a natal-chart card' and enumerates concrete card contents (four pillars, day-master identity, element balance, 왕쇠·격국·용신 verdicts, 신살, 합충). These specifics clearly distinguish it from the related cards among its siblings such as card_fortune, card_timeline, and card_compatibility.

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 clear context for when the tool is appropriate: natal-chart requests such as 사주 봐주세요, 원국 fuh, or 신살 questions. It also states the important precondition that narrative fields must be grounded in a prior legend_saju_read_fortune call. However, it doesn't explicitly contrast against sibling card tools or give a 'use this, not that' rule.

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