Marseille: Interpret

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful context the annotations lack — the POST endpoint and a concrete cost of 10 credits (Tier 1) — but says nothing about per-card versus combined interpretation, the 15-card ceiling, or how output scales with input size.

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?

One sentence followed by compact metadata lines; purpose is front-loaded and nothing is padded. The indirection of putting cost and requirement in bracketed tags is efficient, though the sentence itself is thin for a paid endpoint.

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 needn't be described, and cost/endpoint are disclosed. Still, for a paid interpretation tool with an undocumented question parameter, the agent is left guessing whether the question shapes the reading and whether multiple cards are interpreted individually or as a whole.

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 33%, so the description must carry weight; it does clarify the crucial fact that the cards array holds slugs rather than names or IDs. However the "question" parameter is never mentioned, and it is unclear whether it steers the interpretation, while "art" is already documented in the schema itself.

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?

"Resolve list of card slugs into meanings" gives a specific verb (resolve) and resource (card slugs → meanings), and the group tag pins it to the Marseille deck. It does not distinguish itself from siblings such as astroway_tarot_marseille_draw_* or astroway_tarot_marseille_clarify, so an agent cannot tell from the text alone when this beats a spread tool.

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 versus the many sibling tarot tools, and no prerequisite such as cards coming from astroway_tarot_marseille_cards. The only usage-relevant data is the boilerplate "Required: cards", which the schema already enforces.

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