search_jobs

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

Annotations already cover read-only/idempotent/open-world, and the description adds critical non-obvious behavior: filters other than keyword/area are silently dropped for non-104 sources, 104 excludes 面議 postings unless include_negotiable=True, and per_page is capped at 30 with page-based pagination. These are traps an agent would otherwise fall into.

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 and return shape are front-loaded in the first line, and every subsequent line adds concrete constraint information with no filler. The one drawback is density: parameter rules are packed into a continuous stream without line-level labels, which slows scanning for a 16-parameter tool.

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 16-param tool with no output schema and zero schema descriptions, the description covers the highest-risk areas (source-specific filter support, salary unit, experience matching, pagination) and states the return is a table. It falls short by leaving job_type, new_only, education, and sort partially or wholly unexplained.

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 0%, so the description carries the full burden; it explains keyword/keyword_en interplay, Chinese-name conventions for area/jobcat, the salary_min↔salary_unit coupling, include_negotiable, my_years, and pagination limits. However job_type, new_only, education, and the full semantics of the sort enum are never mentioned, leaving four parameters undocumented anywhere.

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 ('搜尋職缺，回傳表格') and immediately clarifies the return shape plus downstream routing (id → get_job, company_id → get_company). It distinguishes itself from the detail-fetching siblings but never clarifies its relationship to salary_overview or sources, so sibling differentiation is incomplete.

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 explicit routing rules: keyword is Chinese for 104, keyword_en is English for other sources, and when only one is supplied both are shared. It also documents which filters are honored per source (yourator → sort=newest, boards → remote_only) and that unsupported conditions are not silently applied, which is exactly the when-to-use/when-not-to-use guidance an agent needs.

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