Analyze public salary data from Taiwan job postings to report sample counts, minimum, quartiles, median, and maximum pay by unit. Filter by keyword, area, job category, education, or remote status.
薪資行情：取前 pages（1~5）頁有公開薪資的職缺，依單位統計筆數、最低、四分位、中位、最高。 參數同 search_jobs。樣本統計，非全站。
| Name | Required | Description | Default |
|---|---|---|---|
| area | No | ||
| pages | No | ||
| jobcat | No | ||
| keyword | No | ||
| job_type | No | ||
| my_years | No | ||
| new_only | No | ||
| education | No | ||
| remote_only | No |
Changes observed during successful MCP inspections.
v1.1.2Input schema / properties / education / enumAdded value: +[
+ "高中職",
+ "專科",
+ "大學",
+ "碩士",
+ "博士"
+]Input schema / properties / job_type / enumAdded value: +[
+ "全職",
+ "兼職",
+ "高階",
+ "派遣"
+]v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower. The description adds two genuinely useful behavioral facts beyond annotations: the pages 1~5 window and the caveat that these are sample statistics, not the whole site (非全站), which materially affects how results should be interpreted.
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?
Three compact clauses: what it returns, where to find parameter docs, and the sampling caveat. Front-loaded with the resource and scope, 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?
For a read-only aggregate tool with no output schema, the description does state the returned statistics (count/min/quartile/median/max) and the sample-vs-full-site limitation, which is solid. But with 9 undocumented parameters and only a pointer to a sibling tool, an agent cannot confidently supply filter arguments.
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% across 9 parameters, so the description must carry the burden. It clarifies only the pages range (1~5) and otherwise defers with '參數同 search_jobs', leaving area, jobcat, keyword, job_type, my_years, new_only, education and remote_only entirely undocumented in either schema or description, and requiring cross-tool inference.
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+resource: it fetches the first pages of job listings that publish salary and computes per-unit statistics (count, min, quartile, median, max). This clearly distinguishes it from search_jobs (raw listings) and get_job (single posting). It is not quite a 5 because the '依單位' grouping key is left implicit.
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 use case (aggregate salary stats rather than raw job results) and notes '參數同 search_jobs', routing the agent to that sibling for parameter knowledge. However it never states explicitly when to prefer this over search_jobs or any when-not condition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.