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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the description is not burdened with the safety profile. It adds genuinely non-obvious methodology: returns are market-cap weighted, YoY figures are aggregated against the same quarter last year, and per/pbr sort ascending. It does not mention row counts, defaults for limit, or pagination.

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 metric inventory is front-loaded and dense, and each clause carries information about a distinct output field. The '[국내 주식 + 채권 MCP FinQuest]' branding prefix and repeated tool title are overhead, but the body is efficient.

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 must describe returns, and it does so field by field, including the comparison basis for growth metrics. What remains missing is operational detail (default and maximum limits, KOSPI/KOSDAQ filtering, ordering semantics for non-per/pbr sorts), which a caller might still need.

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 50%; the description meaningfully supplements 'industry' (accepted examples like '전기·전자', '제약', '은행', and the omit-for-full-table behavior) and indirectly reinforces sorting by returns/PER. However, 'market' and 'limit' are never addressed in the description, and both are undocumented in the schema, so the gap is only partly closed.

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 names the resource (업종/industry) and enumerates the exact measures produced: company count, market cap, 1/3/12-month cap-weighted returns, aggregate PER/PBR/OPM, and YoY quarterly revenue/operating-profit change. That level of specificity makes it hard to confuse with company-level siblings such as company, valuation, or rank, though no sibling is named explicitly.

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 trigger questions ('어느 업종 실적이 좋아지나', '반도체 업종 PER', '업종별 수익률') and states the fork for the industry parameter: supply it for one industry plus its company list, omit it for the full industry table. There is no explicit when-not guidance or named alternative tool, which keeps it short of a 5.

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