find_related_news

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

Since no annotations are provided, the description bears the full burden of disclosing behavior. It explains the date_range behavior (defaults to today when not specified), the threshold semantics (higher = stricter), and the include_url flag (defaults to False to save tokens). This is good transparency about parameter-driven behavior. However, it doesn't disclose what happens if no related news is found, whether the tool makes external API calls, or any rate limits or performance considerations. It does note that `include_url` defaults to False to save tokens, which hints at token consumption.

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 a clear intro sentence, a list of parameters with explanations, a Returns section, and Examples. It's front-loaded with the purpose and uses bullet points for parameters. While it's somewhat long (9 bullet points for parameters), each point adds distinct information. The examples are concise and useful. It earns a 4 because the structure is organized and information is dense without redundancy.

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 has 5 parameters, an output schema, and no annotations, the description is fairly complete. It covers parameter semantics, return format (JSON list sorted by similarity), and provides examples. The output schema exists, so the description doesn't need to detail return fields, but it mentions sorting by similarity which is useful. It could add more about edge cases (empty results, error handling) or mention similarity computation method, but overall it's adequate for a complex tool with 5 parameters.

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 schema has 0% description coverage, meaning the description is the only source of parameter meaning. The description does explain all 5 parameters: reference_title (full or partial), date_range (options with format details), threshold (range 0-1, default 0.5), limit (default 50), include_url (default False). This is a thorough explanation that adds value beyond the raw schema (which only has types and defaults). However, it could provide more detail on the exact format of the date_range object (it says 'start' and 'end' but the schema just says 'additionalProperties' for the object, so the description clarifies). The threshold explanation is minimal but the default and range are given.

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 the purpose clearly: '查找与指定新闻标题相关的其他新闻' (find other news related to a specified news title). It specifies what it does (find related news based on a reference title) and supports both current and historical data. This is a clear verb+resource combination. However, it doesn't explicitly distinguish from sibling tools like search_news or get_news_by_date, though the term 'related' implies semantic similarity rather than exact search.

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 specifies when to use it via the 'reference_title' parameter and provides examples that illustrate usage. It mentions date_range options, which gives context on when to use historical vs. today-only queries. However, it doesn't explicitly state when NOT to use this tool vs. alternatives (e.g., search_news for exact text matching). The examples are helpful but not exhaustive.

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