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

The description adds meaningful behavior beyond annotations: chart facts are computed server-side, the assistant must write the card/narrative text itself, and the card labels it as AI interpretation. It also tells the agent how to behave after rendering — add only brief text not already shown. This is consistent with the readOnlyHint and destructiveHint 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 packed with actionable guidance: what to render, which domains to pick, how to write text, how the tool works server-side, and what post-render behavior is expected. Every sentence earns its place and no schema detail is redundantly repeated.

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 description is complete enough for an agent to invoke the tool correctly: it specifies the domain scope, the authoring responsibility, the grounding prerequisite, the rendering behavior, and the expected follow-up action. The output schema covers return values, so the description does not need to restate them.

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?

The schema already documents many fields well, including timezone and calendar semantics. The description adds key semantics that the schema does not: which domains to include, that text fields must be assistant-written and grounded in a prior fortune call, and that the card labels interpretation as AI-generated. It does not elaborate on score, title, actions, or asOfYear, but these are sufficiently documented in the input schema.

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: render domain fortune cards, and enumerates the exact domains. It also clarifies that only the user-requested domains should be selected, which clearly differentiates this from sibling card tools like natal, compatibility, or timeline cards.

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 usage guidance: pick only the domains the user asked for, ground the text in a prior legend_saju_read_fortune call, and keep post-render text minimal. It does not explicitly name alternative card tools, but the domain list and the prerequisite from the prior fortune call give enough context for an agent to route correctly.

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