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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds that the verdict comes from 'card affinity', which is some context, but doesn't detail how the affinity is computed, what the output includes (e.g., card, verdict, explanation), or any constraints like credit cost (though cost is listed separately in the description as '[Cost: 10 credits (Tier 1)]'). The cost info is useful but not a behavioral trait beyond annotations. With annotations covering safety, the description provides minimal additional behavioral insight.

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 very concise: one sentence plus two bracketed lines for group and cost. It's front-loaded with the core purpose. However, the bracketed lines, while useful, could be considered somewhat extraneous for a tool description, but they add essential context (group and cost). Overall efficient.

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?

Given there is an output schema (has output schema: true), the description needn't explain return values. However, with 5 parameters and only 40% schema description coverage, the description should provide more guidance on parameter usage. It also lacks any mention of when to use this tool versus the numerous other tarot draw tools. The description is minimal and doesn't fully equip an agent to invoke the tool correctly without additional inference.

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 40%, meaning many parameters lack descriptions in the schema. The description doesn't mention any parameters (seed, fields, question, precision, allowReversed) or their roles. However, the parameters are somewhat self-explanatory by name (e.g., 'question' for the query, 'seed' for randomness). Since the schema has some descriptions (for fields and precision), baseline 3 is appropriate, but the description fails to compensate for the low coverage by explaining the purpose of parameters like 'allowReversed' or 'question'.

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 states a specific verb and resource: 'Single-card draw with yes/no/maybe verdict from card affinity.' This clearly distinguishes it from sibling tools like astroway_tarot_rider_waite_draw_single (single card) and draw_three_card, by specifying the output is a yes/no/maybe verdict. However, it doesn't explicitly name an alternative or state that it's for decision-making questions, which the tool name implies.

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 implies usage by saying it's for a yes/no/maybe verdict from card affinity, but it doesn't explicitly state when to use this tool versus alternatives. There are many sibling tools for different tarot spreads; the description could specify that this is for decision-making or binary questions. The context is implied but not explicit.

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