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

Annotations already convey read-only, non-idempotent, closed-world; the description adds genuinely new behavioral facts: cryptographically secure RNG, cards always upright, nothing is stored, and the citation/attribution obligation. These are things an agent cannot derive from the annotation hints.

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?

Dense but efficient: the randomness/scope statement is front-loaded, followed by return contents, input constraints, and citation duty in that order. It is a long run-on sentence and some clauses (e.g., the 440:827 frame detail) are heavy, but each piece carries information rather than restating the name.

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, yet the description still summarizes the salient return fields (card name/number, plate image URL, keywords, tension, reading link), and it covers input constraints, stateless behavior, and attribution. Nothing an agent needs to invoke it correctly is missing.

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 0%, so the description must carry parameter meaning, and it does: it names the language parameter concept, identifies theme as optional with the four values (love, work, decision, self), and clarifies that no question/free-text parameter exists. It doesn't explicitly name 'locale' as the parameter key, leaving a small gap.

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?

Opens with a specific verb and resource: 'Draw 1 card at random among the 78 cards of the Tarot de Marseille,' immediately distinguishing a random draw from the deterministic lookups implied by siblings like marselia_get_card and marselia_list_cards.

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?

Explicitly states 'Takes no question and no free text: only a language and an optional theme,' which tells an agent what input shape this tool accepts, and implying it is not the tool for Q&A or lookups. It doesn't name a sibling alternative directly, so the routing guidance is clear but not exhaustive.

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