cnki_search

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

Annotations already establish read-only and open-world hints, and the description adds meaningful behavioral context: multi-query planning, deduplication, and a specific re-ranking heuristic. This goes beyond the annotations and gives the agent insight into the tool's non-obvious behavior, though it doesn't mention any rate limits or potential response issues.

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 a single, information-dense sentence that front-loads the tool's core behavior. It avoids redundancy and every phrase adds relevant detail about the internal query planning and re-ranking strategy.

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?

While an output schema exists and the annotations cover safety, the description lacks usage context and does not mention any implications of the multi-query planning (e.g., longer execution time). It does not address how search results are returned or how the agent should interpret the re-ranked output relative to a simple search. Overall, it is adequate but leaves the agent without critical context for effective use.

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 67%, with query, mode, limit, and profile described in the schema. The description itself adds no parameter information, but the schema already provides reasonable meaning for most parameters. Year_from and year_to lack descriptions, but their names and boundaries are self-explanatory. The description neither compensates for nor detracts from the schema.

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 explains the tool's internal behavior: planning multiple queries, deduplicating, and re-ranking results based on relevance, abstract, source tier, literature type, and influence. This clearly distinguishes it from sibling tools like cnki_structured_search, but it lacks an explicit verb like 'searches' or a direct mention of the resource being searched (scholarly literature), which prevents a 5.

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 does not state when to use this tool versus alternatives. There is no mention of 'use this for general searches' or 'use cnki_structured_search for field-specific queries'. No exclusions or alternatives are referenced, leaving the agent without guidance for tool selection.

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