Marseille: Yes/No

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 profile is covered. The description adds genuinely useful non-annotation facts: the cost (10 credits, Tier 1) and the endpoint, which matter for budgeting. It does not describe how the verdict is derived (upright/reversed handling relative to allowReversed), leaving a behavioral gap.

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 core clause is front-loaded in five words and there is no padding prose. The three bracketed metadata lines are boilerplate but each carries usable information (endpoint, cost tier).

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-value explanation is not required, and annotations cover the safety profile. But given a 4-parameter tool at 25% coverage sitting among hundreds of tarot/draw siblings, the description should at minimum say what the seed and allowReversed affect and how the verdict is produced. It is minimum viable, not complete.

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 coverage is only 25% — only `art` is documented in the schema. The description says nothing about `question`, `seed`, or `allowReversed` (whose interaction with the verdict is the most consequential parameter here). With three of four parameters undocumented in both places, the description fails to compensate.

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?

"Single-card yes/no with verdict" states a concrete verb-equivalent (draw one card) and a concrete output shape (binary verdict), which distinguishes it reasonably from generic draw tools like astroway_tarot_marseille_draw_single or draw_three_card. It does not explicitly differentiate from the near-identical astroway_tarot_rider_waite_draw_decision (different deck) or from astroway_tarot_marseille_clarify, so it stops short of a 5.

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?

There is no guidance on when to pick this over draw_single, clarify, draw_cross, or the Rider-Waite decision variant. The only added context is group/endpoint/cost metadata, which tells the agent nothing about selection conditions.

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