유사 자료 추천

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

No annotations are provided, so the description must cover behavioral aspects. It states that recommendations come with rationale (shared standards, topics, subjects), which is helpful. However, it does not explicitly state that the tool is read-only (non-destructive) or discuss any side effects, permissions, or rate limits. The verb 'recommend' implies safety, but more explicit transparency would improve the score.

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 two short sentences that are front-loaded with the main action and immediately followed by a usage scenario. Every word is purposeful, and there is no redundancy. It balances brevity with completeness, earning a top score.

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?

Given the tool's moderate complexity (3 optional parameters, no output schema, no annotations), the description covers key aspects: inputs, output content (similar resources with rationale), and usage context. It does not describe return format details like pagination or sorting, but the absence of an output schema lowers expectations. The rationale mention compensates partially.

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 input schema has 100% description coverage for all three parameters, so the baseline is 3. The description adds little beyond the schema: it mentions that resource_id and document_id serve as criteria, but the schema already describes them. The use case context ('비슷한 것 더') provides some semantic enrichment, but not enough to raise the score above baseline.

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 the tool's purpose (recommending similar resources) and specifies the input types (resource_id or document_id). It also includes a concrete use case ('when a teacher wants 'more like this'), which distinguishes it from generic search tools. The verb '추천' (recommend) is specific and indicates a non-search operation.

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 explicitly tells when to use the tool ('when a teacher likes a resource and wants similar ones'), providing clear context. However, it does not mention when not to use it or explicitly compare it to sibling tools like search_resources or explore_topics. The guidance is clear but could be strengthened with exclusion criteria.

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