Search Cnki

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

With no annotations, the description carries the full disclosure burden. It does add genuine behavioral detail — that setting author/journal switches the backend to 专业检索, and that source_category is a result-sidebar group filter with no professional-search equivalent — but it never mentions that this is a browser-session operation needing a login (siblings renew_session and get_login_status imply that dependency) or anything about rate limits or failure modes.

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 stated first, then the critical parameter constraint, then examples — a good front-loaded order with no filler prose. It is slightly redundant with the schema's own query and author descriptions, but the repetition is defensible for a misuse-prone parameter.

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 7-parameter search tool with an output schema (so return values need no explanation), the description covers search semantics, filter composition, and the sidebar-vs-expression caveat ('其他条件…请优先用检索表达式'). An agent can construct a correct call from this plus the schema; the only missing piece is session/auth state, which is minor here.

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%, so the baseline is 3; the description earns above that by repeating and reinforcing the highest-risk parameter rule (never put an author name in query) and by demonstrating parameter combinations in examples. Note the schema already documents sort/pages/search_type/source_category enumerations, so most added value is concentrated in the query-vs-author distinction.

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 opening sentence gives a specific verb and resource plus the return shape: search CNKI papers and return a paper list. The scope is unmistakable against retrieval-oriented siblings like get_paper_detail or read_paper_fulltext, but no sibling is named explicitly, so differentiation is inferred rather than stated.

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 explicit routing rules with a warning ('重要：query 参数只放主题/关键词/篇名，不要把作者名混入 query'), tells the agent which parameter to use instead, and notes that author and query can be combined. Two worked examples ('经济增长' + author='张三'; 'ESG' + source_category='北大核心,CSSCI') remove any remaining ambiguity about how to compose a call.

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