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

The annotations already establish read-only, idempotent, closed-world behavior, so the description adds context beyond that structured data: the values are estimates, not authoritative figures; the unit is 10,000 KRW per year; and omitting 'experience' returns all ranges. Those details matter to an agent interpreting or citing the results. It does not cover data freshness or the granularity of the estimate (for example, a range versus a point value), which prevents a 5.

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 is front-loaded with the core purpose in both Korean and English, then moves into a compact parameter legend. The Korean/English duplication of the purpose sentence is somewhat redundant, and only the Korean line carries the enum legend, leaving the English reader without it. It stays tight overall with no filler.

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?

There is no output schema, and the description compensates by specifying that the return value is an annual estimate in units of 10,000 KRW. Combined with full enum semantics and the default behavior for the optional parameter, this is enough for correct invocation. It does not explain the shape of the response (a single figure versus a table by experience) or the data source and date, so it is not quite complete.

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%, but the schema only labels the parameters '업종 코드' and '경력 코드' with bare enum codes. The description maps every enum value to its Korean business meaning (luxury=럭셔리 패션, cosmetics=뷰티/화장품, etc.) and, crucially, gives the year bands behind each experience code (entry=0년, junior=1~3년 ... lead=10년+). This is real semantic value the schema does not contain.

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: retrieve annual salary benchmark estimates for retail sales staff at luxury brands, department stores and duty-free shops in Korea, broken down by category and experience. It is unmistakable what the tool returns. It does not mention the sibling tools (get_job, search_jobs), so it stops short of explicitly saying how it differs from them, but the subject matter (benchmarks rather than job postings) is inherently distinct.

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 the tool's usage: the output is '추정치/Estimated,' not a live posting, which hints that the tool is useful for reference rather than for finding a job. However, it never says when to call this instead of get_job or search_jobs, and it gives no prerequisites or exclusions. The guidance is implied rather than explicit.

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