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. It does disclose what the tool does NOT do (no reversals, astrology, redraw loop, guaranteed prediction) and the sharing quota, which is helpful. However, it doesn't state what happens to user data, API costs/limits beyond the quota-sharing hint, or whether this is a read-only operation. The behavioral expectations are partial.

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 a tight paragraph front-loaded with the core purpose and output structure, followed by constraints. Every clause earns its place — purpose, output format, disclaimers, quota. Slightly dense but efficient; could arguably be split into clearer sentences but remains readable and scannable.

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 tool has 4 parameters, no output schema, and no annotations, so the description must carry substantial weight. It covers output format, constraints, and quota well. However, it lacks detail on pricing/credits (day quota hints at it), whether the consultation is deterministic vs paid-per-call, response format details, or failure/edge cases like invalid questions. Adequate but leaves operational unknowns.

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 75% (question, seed, locale, device_id described). The description reinforces the key 'question' parameter semantics ('one real question') and the single-card bound. The seed, locale, and device_id are adequately documented in the schema, so the description adds modest value by emphasizing the question qualifier ('real') and single-card constraint.

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 clearly states the verb+resource ('Ask one real question through a single upright Waite-Smith Major Arcana card') and details the output structure (direct answer, named card with Waite 1910 excerpt, reality check, next step). It differentiates from siblings by explicitly noting what it does NOT include (no reversals, astrology, redraw loop), though it doesn't name sibling alternatives directly.

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?

The description gives clear context on when to use it — when a user has 'one real question' — and sets expectations about scope (single card, no redraw, no guaranteed prediction). It mentions the daily quota shared with divine and Two Lenses readings, which is useful operational guidance, though it doesn't explicitly name alternatives like cast_hexagram/tarot for other use cases.

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