Search CNKI / 知网

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

With no annotations, the description must carry the full burden of behavioral disclosure. It does explain parameter constraints (e.g., field enums, sort options) and a conditional rule about query emptiness, which is helpful. But it does not mention pagination size, error behavior for invalid combinations, or what happens when no filters are set. The output schema covers return values, but other behavioral traits remain undisclosed.

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 concise and well-structured: a one-line summary followed by an Args list with every line adding value. There is no redundant information, and the note about query emptiness is placed logically before the parameter list. It is appropriately sized for an 8-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?

The description covers all parameters with semantics and provides a conditional note, which is solid for a search tool. An output schema exists, so return values are handled externally. However, it lacks explicit reference to sibling get_record for single-record lookups, and does not mention edge cases like page size limits or default field behavior beyond schema defaults. Minor gaps keep it from a perfect score.

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?

The description provides meaningful explanations for all 8 parameters, going beyond the bare schema. It translates each enum value (theme, title, keyword, etc.), clarifies the meaning of 'page', and offers a practical tip ('Exact title works best with field=title'). This is exactly what parameter semantics should provide, and the schema alone offers no descriptions.

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 clearly states it searches 知网空间 metadata with a specific verb ('Search') and resource, and the parameter list distinguishes it from get_record by focusing on multi-field querying rather than single-record retrieval. The purpose is immediately understandable and not a tautology.

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?

There is a useful note about 'query may be empty if author or advisor is set', giving conditional usage guidance, and the parameter explanations imply how to use search. However, there is no explicit statement of when to use this tool versus get_record, nor any mention of alternatives or exclusions. This is a missed opportunity for clear guidance.

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