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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered. The description adds behavior those annotations cannot express: the cost (100 credits, Tier 4), the structure of what the AI returns, and multilingual output. It does not explain the non-idempotent nature of repeated AI readings, but the added cost and output detail is real value.

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 narrative is front-loaded in one dense sentence covering purpose, input flexibility and output shape, with the metadata block (group, endpoint, required, cost) compactly appended. No sentence is wasted; the only minor cost is that parameter detail is omitted rather than trimmed.

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 described, and cost plus required input are stated. However, for an 8-parameter tool at 38% schema coverage, an agent still lacks guidance on spread, question, art, fields and precision, making the definition only minimally sufficient.

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 38%, so the description must carry more of the parameter burden. It covers the two most important ones implicitly (cards accepts slugs or a draw array; language = 'Multi-language'), but art, deck, spread, question, fields and precision get no mention at all, leaving six parameters explained only by terse or absent schema text.

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?

Specific verb+resource with a clear scope: an AI reading of a spread across three deck systems, with the output shape (per-position reading, synthesis, one piece of advice) spelled out. It doesn't explicitly distinguish itself from the deck-specific siblings astroway_tarot_marseille_interpret or astroway_tarot_rider_waite_interpret, which is the remaining gap.

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?

'Takes card slugs or the drawn array of any draw response' implies the intended workflow (call this after a draw tool) but never states that directly, and gives no guidance on when to prefer the deck-specific interpret siblings over this cross-deck tool. Usage is inferable rather than stated.

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