aggregate_news

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

No annotations are provided, so the description carries the full burden, which it handles well: it discloses that similar stories get merged, that similarity_threshold controls strictness (越高越严格), and that the result includes dedup statistics, the aggregated list, and platform coverage stats. It does not state its read-only nature explicitly, but all params are query filters, so that is safely inferable.

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?

Well structured: one-line summary, prose explanation, then Args/Returns/Examples sections. The purpose is front-loaded. It is a bit long, but justified because it must carry all parameter documentation that the 0%-coverage schema omits. No wasted sentences.

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?

Covers all parameters, defaults, and return shape (even though an output schema exists, so returns were optional). The only real gap is the date_range value format — the schema allows object or string, and the description just says '日期范围' without specifying accepted formats (e.g., ISO dates, relative strings) — a minor ambiguity for a complex tool with zero schema descriptions.

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 fully — and it does. The Args block documents all 5 parameters with semantics, valid ranges (0.3–1.0 for similarity_threshold), defaults (50, 0.7, False), and examples (['zhihu', 'weibo']). This is textbook compensation for an empty 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?

States a specific action (deduplicate and merge similar news across platforms into one aggregated item) with a distinct resource (cross-platform news). The first line '跨平台新闻聚合 - 对相似新闻进行去重合并' plus the fuller explanation of merging same-event stories and showing cross-platform coverage clearly separates it from siblings like get_latest_news, search_news, and find_related_news.

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 implies its use case: seeing combined cross-platform coverage with heat and dedup stats rather than raw per-platform lists. However, it never explicitly names alternatives or states when not to use it. Given ~27 sibling news tools, explicit routing (e.g., 'use get_news_by_date for a single day's raw items') would materially help an agent.

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