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

Annotations mark it non-read-only and open-world, and the description adds genuinely useful behavior beyond them: the deterministic mulberry32 RNG tied to `seed`, the daily-seed fallback when omitted, and the effect of `allowReversed`. It does not mention the 100-credit cost, but determinism disclosure is exactly the kind of context an agent benefits from here.

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?

Front-loaded with the action and default, then parameter behavior. The ten-item spread list is long but justified because `spread` is a plain string in the schema with no enum, so this is the only place the valid values appear. The trailing text is truncated, slightly hurting readability.

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 need not be explained, and the core generation parameters are covered. However, several configurable inputs (language, whitelabel theming, fields/precision compact mode) are neither in the description nor documented in the schema, leaving meaningful gaps for a tool with 8 parameters.

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% across 8 parameters, so the description must compensate. It explains `spread` (with the full valid list, since the schema types it as a bare string), `seed`, and `allowReversed`, but leaves `language`, `whitelabel`, `fields`, `precision`, and `name` entirely undocumented. Partial compensation only.

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 ('Render') and resource ('tarot reading PDF') and immediately characterizes the default output (three-card Past/Present/Future from Rider-Waite-Smith). Tarot is unambiguous against all report siblings, which cover natal, synastry, vedic, etc.

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 explains how to use the tool (spread options, seed for reproducibility, omit for daily seed, allowReversed toggle) but never says when to choose this over the other report generators or what prerequisites exist. Usage is implied by parameter behavior rather than stated as guidance.

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