RWS: Shadow Work

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

Annotations already declare readOnly=true, idempotent=true, destructive=false, openWorld=false, so the safety profile is covered. The description adds genuinely useful non-schema context — the POST endpoint and the 10-credit Tier 1 cost — but says nothing about whether the supplied seed makes results reproducible or how allowReversed changes the output.

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 substantive line is five words and fully front-loaded; nothing is padded or hedged. The remaining lines are boilerplate group/endpoint/cost metadata, which is useful only in the cost/endpoint part but consumes most of the character budget.

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?

An output schema exists, so return values needn't be explained. Yet for a tool with four optional parameters and heavy sibling competition, the description omits the one thing the schema cannot convey: when a shadow-work spread is the right choice and what the six card positions mean.

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 only 25%: only `art` is documented, while `seed`, `question`, and `allowReversed` carry no schema text at all. The description adds zero parameter guidance, so an agent has no explanation of what the question is used for or how seed/allowReversed affect the drawn cards.

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?

"6-card shadow integration spread" identifies a specific artifact (a six-card RWS tarot spread), and the tool name supplies the draw verb. However the description is a bare noun label — it never states the action, what a shadow integration spread is, or what the six cards represent, so the agent must infer usage from the name alone.

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?

No when-to-use, when-not-to-use, or alternative routing is offered, despite many close siblings (draw_three_card, draw_spiritual_path, draw_chakra, shadow_card). Nothing tells the agent how to choose a shadow-integration spread over any other RWS draw or over the single-card shadow card lookup.

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