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

With all annotations set to false, the description carries the full burden and delivers: it reveals that each row uses 'the price card_price returns for that card_id (its headline grade, usually PSA 10 or CCIC 10) with price_basis = verified_sales or reference,' that 'Cards with no usable price are not ranked,' that the response reports how many cards have a usable price, that it has no paging, and that calls 'record usage and query metadata.' This is extensive behavioral disclosure beyond what any annotation or schema provides.

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 description opens with a clear one-sentence purpose statement and front-loads the core ranking behavior. It includes a bilingual note and example queries that occupy space, and some redundancy exists between the first sentence and the quoted examples. Still, every sentence adds a distinct behavioral fact or clarification, so the length is justified rather than padded.

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?

The description is complete for a tool with an output schema and fully documented parameters. It covers language-track nuances, top-N limit behavior, handling of cards with no usable price, absence of paging, and metadata recording. Edge cases such as multiple language tracks and the reported count of ranked cards are addressed. Nothing an agent needs to call or interpret the result is left to inference.

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 the baseline is 3, but the description adds meaningful semantics for the lang parameter: it clarifies that lang refers to the card's print language, not the user's language, warns that 'Prices are never mixed across tracks,' and explains the omission behavior when a set exists on only one track. The set_code parameter also gets examples (m2a, 151c, CEL). This is value beyond the schema's own parameter descriptions.

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 first sentence states a specific verb and resource: 'Rank the highest-priced cards inside one Pokémon TCG set, on one language track (top N, max 20).' It further distinguishes itself by explicitly saying it is 'not a price-sorted checklist and has no paging,' which separates it from any list-returning sibling. The description also provides concrete example queries ('Answers "most expensive / top 5 priciest cards in m2a"'), leaving no ambiguity about what the tool does.

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?

The description implies when to use this tool versus manually checking individual cards ('不用逐张查价' — no need to check prices one by one) and references card_price as the pricing source. It defines boundary conditions like 'on one language track' and 'no paging,' but it does not explicitly name alternative sibling tools or state when NOT to use this tool. This is clear context without formal exclusions.

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