Marseille: Clarifier

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context — the POST endpoint and the 10-credit Tier 1 cost — which helps an agent budget calls, but it says nothing about whether the draw depends on a prior spread or what the card selection behavior is.

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 sentence is front-loaded and wastes no words, and the bracketed group/endpoint/cost lines are compact. It is short enough that nothing needs cutting, though the metadata lines add no descriptive value.

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 values need not be explained, and annotations cover safety, so the bar is lower. Still, for a 4-parameter tarot draw the description never clarifies whether this is a standalone reading or a follow-up to an existing spread, nor how seed/allowReversed affect the result — a gap an agent cannot resolve from the fields provided.

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%, with just the 'art' parameter documented, so the description carries the burden of explaining question, seed, and allowReversed — and it explains none of them. 'Single clarifying card' gives no hint that a question or seed can be supplied, meaning the low-coverage parameters are undocumented in both places.

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 says 'Single clarifying card,' which identifies the resource (a one-card tarot draw) but leaves the verb implicit and never distinguishes it from close siblings such as astroway_tarot_marseille_draw_single or astroway_tarot_rider_waite_clarify. An agent can infer a one-card Marseille pull but must guess how a 'clarifying' draw differs from a plain single draw.

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 statement of when to use this tool, when not to, or which sibling to prefer. The only added context is the endpoint and credit cost, which is operational metadata rather than usage guidance.

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