find_related_news

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

No annotations are provided. The description carries full Burden: It reveals the default behavior (reference date defaults to today), the meaning of threshold (higher = stricter match), include_url (to save tokens), and return format sorted by similarity. It covers the main behavioral expectations but does not detail edge cases like error conditions, pagination, or the event when no matches are found.

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 structured with Args, build returns, and rater examples. It is comprehensive but still readable. It includes only required details, defaults emphasized. It might be slightly nitrogen but not verbose. The content is front -loaded with the main purpose and parameter meaning, so Concise them. Score 4 for good structure without verbosity.

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 5 parameters, 1 required, an output schema, the description is adequately complete: it provides defaults for every parameter, illustrates different styles date_range, states the return type (JSON sorted by similarity), and offers usage examples. It does not mention pagination, but that also lies in output schema and defaults. The level of detail matches the tool complexity and the schema information.

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 antecedent has 0% schema coverage; every parameter listed in the schema has no description property. The description provides a full Args block that explains each parameter meaning, its (date preset and custom JSON format), default values, and the effect of similarity threshold and include_url. Includes examples; this is exactly the compensation needed for low schema coverage.

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 explicitly states: it finds other news related to a given news title ('查找与指定新闻标题相关的其他新闻'), and supports both current and historical data. This is a specific verb-resource pair that clearly distinguishes it from sibling tools like get_news_by_date (date–based) or search_news (generic search). An agent reading the first sentence knows exactly what tool does.

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 provides usage examples and explains parameter behavior (e.g., '不指定只查询今天的数据'), but it does not explicitly instruct when to use this tool over search_news, get_news_by_date, or other siblings. It covers the da:definitions of arguments, but leaves the selection criteria to inference. The 'If not specified' etc. shows usage context for the tool, but not when to pick it over its peers.

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