search_rss

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

With no annotations, the description carries the full burden and does disclose useful behavior: default time window (默认 7 天), max window (最大 30 天), all-feed scope when feeds is omitted, and JSON return format. It leaves gaps on matching semantics (exact vs fuzzy, title vs full-text), behavior with zero matches, and result ordering.

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-organized into purpose, Args, Returns, and Examples with the purpose front-loaded. The examples earn their place. Minor redundancy: defaults restated in Args (默认 7 天, 默认50, 默认False) duplicate what the input schema already displays.

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?

For a 5-parameter tool with zero schema descriptions and no annotations, the description covers purpose, every parameter's meaning, defaults, and return format; an output schema exists so return values need not be spelled out. Missing only the source of valid feed IDs (e.g., via get_rss_feeds_status) and match semantics.

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 Args block must fully compensate — and it does. All five parameters (keyword, feeds, days, limit, include_summary) receive meaningful semantics, and it adds a constraint the schema lacks (days 最大 30 天) plus the all-sources default behavior for feeds.

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 — '在 RSS 订阅数据中搜索包含指定关键词的文章' — with a clear verb (search), resource (RSS subscription data), and intent. It is distinguishable from siblings like get_latest_rss by the keyword-search focus, but it does not explicitly differentiate itself from search_news, leaving some discrimination to the agent.

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 Args section gives conditional guidance ('不指定时：搜索所有 RSS 源') and the Examples show plausible invocations, which implies usage context. However, it never states when to prefer search_rss over siblings like search_news or get_latest_rss, nor any exclusions.

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