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

Annotations are all false hints and carry almost no signal, so the description shoulders the burden — and it delivers: it discloses that calls record usage and query metadata (consistent with readOnlyHint=false), and it corrects a likely misconception by stating counts are catalog facts, NOT pull-rate probabilities. No contradiction with annotations.

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 primary purpose is front-loaded in the first sentence, which is good. However, the full Chinese translation duplicates the English content nearly verbatim, roughly doubling length without adding agent-useful information; the not-probabilities caveat and metadata note are valuable, but the bilingual block is bloat for an AI consumer.

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 is present, so return-value documentation is covered elsewhere. The description supplies purpose, the question it answers, variant semantics, a misuse warning, and side-effect disclosure — adequate for a two-parameter set-scoped query tool. Only explicit sibling differentiation 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 100%, so both parameters (set_code, lang) are already documented, meeting the baseline. The description adds domain context about what variants (base/Master Ball/Poké Ball) mean and that lang is a language-track filter, but it does not add parameter-level syntax or format details beyond the schema — marginal added value.

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?

States a specific deliverable — a per-Pokémon breakdown of card faces and variant splits for one set — with a concrete question it answers ('which Pokémon has the most versions in this set'). The verb 'breakdown' plus the set-scoped resource make the purpose clear, though it never names a sibling it is not, leaving slight overlap ambiguity with get_set_overview.

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?

Use case is implied through the 'Answers X' line and the set-scoped framing, which distinguishes it from market tools like card_price and recent_sales. However, there is no explicit when-to-use vs when-not-to-use guidance, nor any named alternative for overlapping set-level queries, so routing is left to inference.

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