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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety bar is met. The description adds genuine behavioral context that annotations cannot: what the call returns (card identities plus localized reference-page URLs) and that names are the canonical historical plate names — valuable since there is no output schema.

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?

Two tight sentences with the verb and resource front-loaded. Every sentence contributes: the first defines output, the second defines the naming convention.

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 simple, unpaginated enumeration with one optional parameter and no output schema, the description covers return content adequately. The only real gap is not clarifying the scope of the locale parameter's effect (URLs vs. names).

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 single 'locale' parameter has 0% schema description coverage, so the description must carry the load. It only implies localization via the phrase 'localized reference-page URLs', without stating that locale controls this, listing the supported values, or clarifying whether names are also localized.

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 ('List') with a precisely quantified resource ('78 Tarot de Marseille card identities and localized reference-page URLs'). An agent can distinguish this from marselia_get_card, though the description never names the sibling it is not.

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?

No when-to-use guidance, no exclusions, and no named alternatives such as marselia_get_card for a single card's full details. The note about canonical historical names is semantic color rather than routing guidance, so the agent must infer when this beats fetching a specific card.

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