search_knowledge_points

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

No annotations are provided, so the description carries the full burden. It does not disclose whether this is a safe read-only operation, whether it requires permissions, whether results are paginated, or how the search behaves (e.g., exact match vs full-text). The bare return format '知识点列表' is thin behavioral context.

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 response is front-loaded with the core purpose, followed by a structured parameter list and a brief return summary. It is compact and every sentence serves to clarify invocation. Slightly verbose in enumerating category values, but that is necessary for an agent to pick valid values.

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?

With no annotations and a 0% schema description coverage, the description steps in to cover all three parameters and the return shape, which is adequate. However, it does not describe pagination, ordering, or how to handle an empty result, leaving minor gaps for a search tool. Since an output schema exists, return values need not be fully explained, so the description's summary suffices.

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%, so the description must compensate. It explains each parameter: query is a keyword in Chinese or English with concrete examples ('现在完成时', 'since'), category limits to specific large classes (词法/句法/时态/语态/非谓语/综合复习), and limit controls the maximum number returned. This adds substantial meaning beyond the schema, though limit's type and default are only in 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 states a clear verb and resource: '按关键词检索语法知识点' (retrieve grammar knowledge points by keyword). It distinguishes from siblings like get_knowledge_point (singular retrieval) and list_lectures (a different resource), though it does not explicitly name them. The purpose is specific enough for an agent to know this is a search operation over knowledge points.

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?

Usage is implied by '按关键词检索' (search by keyword), but there is no explicit statement of when to use this tool versus alternatives such as get_knowledge_point or find_by_relation. The parameter descriptions hint at refining searches with category, but no exclusion conditions or preferred scenarios are given.

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