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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely useful operational context: cost (10 credits, Tier 1) and the exact endpoint. It does not disclose the draw's randomness or how seed/allowReversed affect reproducibility, which is the remaining behavioral gap.

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 core purpose is front-loaded in a single line, with metadata in tidy bracketed blocks. Nothing is verbose or padded, though the endpoint/group lines are conventional noise rather than decision-relevant content.

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 no-required-parameter draw tool with an output schema, the definition covers purpose, cost, and endpoint adequately. It omits any auth requirement and the meaning of the spread's six positions, and gives no hint about determinism despite an idempotentHint, leaving the agent slightly under-informed about what it will actually receive.

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 only 50% (seed, question, and allowReversed carry no descriptions), and the description adds no parameter meaning at all. It does not explain that seed makes the draw reproducible, nor that allowReversed toggles reversed-card output. No compensation for the coverage gap.

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 phrase '6-card three-person love dynamics' pins down the spread size (6 cards), the subject (three people), and the domain (love/relationships), which separates it from siblings like draw_relationship or draw_celtic_cross. However it is a noun fragment with no explicit verb, so the agent must infer that it draws/deals cards. The alias note further disambiguates it from astroway_tarot_rider_waite_draw_love_triangle.

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?

Nothing states when to pick this over astroway_tarot_rider_waite_draw_relationship, the canonical non-alias love_triangle, or astroway_ai_interpret_tarot. The alias note is a dedup hint, not usage guidance. No prerequisites, exclusions, or alternative-selection logic are given.

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