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

Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds substantive context beyond them: the data provenance (계산된 지표 from 사업보고서 '사업의 내용' 표) and inline metric semantics such as 수주잔고÷매출(몇 년치 일감), which tells the agent what the numbers actually mean. It omits coverage caveats (only companies disclosing such tables) and units.

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?

Purpose is front-loaded in the first clause, then the metric vocabulary, then the filtering scope, then examples, ending with the empty-`by` rule. The long enum enumeration earns its space because it defines the parameter domain; no filler sentences.

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 9 parameters, no output schema, and only light annotations, the description handles the metric vocabulary and filters well but never says what a result row contains (company + metric value + market + fiscal year?) or the default sort direction when `ascending` is omitted. Enough to call it, not quite enough to predict the response shape.

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 78%, so the baseline is 3, but the description meaningfully maps Korean metric concepts onto the `by` enum values (수출 비중, 최대 고객 매출 비중, 평균 가동률, 수주잔고÷매출, 연구개발비/매출, 당사 시장점유율) and explains that market/industry/theme are narrowing filters. It says nothing about `min`/`max`/`limit`/`ascending`, which the schema only partly documents.

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 and resource ('사업 지표로 회사들 줄 세우기') and enumerates the exact metric family drawn from 사업보고서 '사업의 내용' tables, which makes it clearly distinct from a generic price/valuation ranker. However, it never names the sibling `rank` or `screen` to draw the contrast explicitly, leaving the agent to infer the boundary.

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?

Gives concrete example questions that should route here ('수출 비중 높은 회사', '수주잔고 많은 조선사', '증설 많이 한 회사'), plus a real usage rule: leaving `by` empty returns the metric list, which is a discovery pattern. It stops short of stating when NOT to use it (e.g. for price/valuation rankings use `rank`).

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