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

Adds context beyond annotations: the 24h session expiry and the hosting constraint ('standalone/npm build returns session_supported:false') are not derivable from structured fields. One tension: it creates/reshuffles server-side session state while readOnlyHint=true, which an agent might misread, though it is non-destructive ephemeral state.

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 with the scoping and consequence front-loaded; the hosting caveat trails but is worth keeping. No wasted clauses.

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?

No output schema exists, and the description covers lifecycle (open/reshuffle, expiry) and the session_supported flag, which is enough to call it correctly. It says nothing about what a successful open returns (e.g., the session_id itself), a minor gap.

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 coverage is 100%, so seed (deterministic order) and session_id (reshuffle existing) are already documented. The description reinforces the cross-tool semantics of session_id but adds no syntax or format detail, so the baseline 3 applies.

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 specific verb and resource ('Opens (or reshuffles) a stateful 78-card tarot session') and names the sibling tools (random_card/draw_cards/tarot_spread) it feeds, so an agent can distinguish it from those without opening schemas.

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?

Explains the condition that motivates the call: use it so subsequent draws with the same session_id avoid repeats until reshuffle/expiry. It doesn't state when NOT to use it (e.g., when a fresh random draw suffices), which keeps it short of a 5.

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