주식 랭킹 조회

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

Annotations already declare read-only, non-destructive behavior, but the description adds substantial extra context: a documented error code for the realtime+TOP_GAINERS combination, the fact that fewer than `count` results can come back because failed quotes are excluded, empty `rankings` with null `rankedAt` instead of an error, and a rate-limit group. That's exactly the kind of failure-mode disclosure annotations don't cover.

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?

A summary sentence followed by tight bullets, each carrying distinct information (unsupported combo, aggregation basis, basePrice/changeRate meaning, count shortfall, empty-result shape). No sentence restates the title and nothing is 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?

For a 5-parameter tool with no output schema and no schema-level parameter docs, the description is unusually complete: it covers output shape, error conditions, and the meaning of returned fields like basePrice/changeRate. The remaining gap is `excludeInvestmentCaution` and any default for `count`, both 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?

With 0% schema description coverage the description must carry parameter meaning, and it does for `type` (grouped enum semantics), `duration` (realtime unsupported for top gainers/losers), and `count` (100 max, effective count may be lower). `excludeInvestmentCaution` is never mentioned, and `marketCountry` is only named as a filter without further elucidation.

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 states a specific verb and resource ('주식 랭킹 조회') and scopes the result ('상위 100위까지 제공'), keyed to market/duration/type. It never explicitly distinguishes itself from the sibling toss_get_sector_rankings, so an agent must infer that this is per-stock ranking rather than per-sector.

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 gives concrete conditions: TOP_GAINERS/TOP_LOSERS reject duration=realtime with a 400 unsupported-ranking-duration, and TOSS_SECURITIES_* types use different aggregation bases than MARKET_*/TOP_* types. What's missing is routing guidance naming which sibling to use instead when the caller wants sector-level or individual price data.

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