Tarot Cards Catalogue

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety behavior. The description adds transparency by describing it as a standalone catalogue endpoint and linking to the full output and error contract. It does not contradict the annotations, and the additional context is sufficient without being redundant.

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 well-structured with clear sections (WORKFLOW, INPUT CONTRACT, DO NOT CONFUSE WITH) and a link to documentation. It is slightly verbose because it repeats response_format information from the schema and lists many output fields, but every sentence adds value and the organization makes it easy to scan.

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 tool that returns a large deck with many fields and has only one parameter, the description covers everything needed: the output content, the parameter semantics, the use context, and how it differs from siblings. The link to the full output and error contract further ensures completeness. No output schema is provided, but the description explicitly lists the output fields.

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?

The sole parameter response_format is fully described in the input schema with an enum of markdown/json, a default, and a clear explanation of what each format returns. The description also repeats this in the INPUT CONTRACT section, ensuring complete semantic clarity. Schema coverage is 100%.

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 tool returns the complete 78-card Rider-Waite-Smith deck with full metadata, listing the specific fields (id, name, arcana_type, etc.). It also names sibling tools it should not be confused with, making its unique purpose unmistakable.

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 explicitly says when to use this tool versus alternatives via the 'DO NOT CONFUSE WITH' section, noting that major_arcana returns only 22 cards, suit returns only 14 cards, and draw returns a random draw. It also provides workflow guidance (BEFORE/AFTER) indicating it is a standalone catalogue endpoint to be used as a base for display layers.

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