섹터 랭킹 조회

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

Annotations already cover the read-only, non-destructive profile, and the description goes further: it caps results at 100 and warns the count may be lower, explains that sparse sectors are filtered out, specifies nullability rules for tradingAmount/marketCapitalization versus always-present changeRate, and notes US amounts are KRW-converted. It does not describe pagination or ordering within ties, and the rate-limits group is named without any limit value, so it stops short of full behavioral disclosure.

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 framing sentence followed by tight bullets, each carrying a distinct operational fact (scope, exclusion rules, ranking basis, currency handling, empty-result behavior). Nothing is repeated and the most important constraint is front-loaded.

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?

With no output schema, the description steps in and describes the response shape (a rankings array, per-item currency, per-field nullability, possible short counts). Combined with the scope and empty-result rules, an agent has enough to call it and interpret results correctly.

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 description coverage is 0%, so the description must carry the parameter meaning — and it does for the most opaque one, mapping TOP_GAINERS to changeRate and MARKET_TRADING_AMOUNT to tradingAmount. marketCountry and duration are left to their self-explanatory enum values, and the description references a `depth` field that is not actually a parameter of this tool, which is a minor mismatch.

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 verb+resource (섹터 랭킹 조회) and immediately narrows the scope to sector rankings by market, duration and ranking basis, with top-100 coverage. The scope note on 대분류/중분류 (depth 0/1) vs 소분류 clearly separates it from stock-level siblings such as toss_get_rankings and toss_get_sector_stocks.

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?

It explains edge-case outcomes (a combination with no data returns an empty rankings array rather than an error) but never tells the agent when to pick this tool over sector siblings like toss_list_sectors, toss_get_sector or toss_get_rankings. Usage is implied by the scope rather than stated.

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