Aggregate and filter trending tech items from multiple sources with time-window and keyword filters, deduplication, and hotness sorting. Handles partial source failures gracefully.
抓取热点条目：按时间窗过滤、跨源去重、按时间/热度排序。某个源失败不会让整个调用失败，但会列在 errors 里。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | 标题/摘要包含该词（不分大小写） | |
| sources | No | 不传 = 全部源 | |
| windowHours | No | 只看最近 N 小时；无时间的条目不过滤 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes beyond the schema by disclosing partial-failure behavior (failed sources appear in errors), cross-source deduplication, and sorting by time/popularity. With no annotations, this carries the transparency burden well, though it omits auth/rate-limit and response shape details.
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?
Two terse sentences: first states the core behavior, second discloses the partial-failure contract. No filler or repetition.
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 filter criteria, deduplication, sorting, and error handling. Lacks explicit output shape/pagination, but no output schema exists; still enough for basic invocation with zero required params.
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 coverage is 75% and most parameters (query, sources, windowHours) are self-describing. The description adds behavior-level meaning (time-window filtering, cross-source dedup) but doesn't significantly enrich individual parameter semantics beyond what the schema provides.
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 uses a specific verb and resource ('抓取热点条目', fetch hotspot entries) and adds distinguishing behavioral details: time-window filtering, cross-source deduplication, and ordering by time/heat. This makes the tool's purpose immediately recognizable and distinct from the sibling list_sources, which is about listing sources rather than fetching entries.
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 when to use it (fetching hotspots with filtering/dedup/sorting) but gives no explicit guidance on when not to use it or how it compares to list_sources. An agent can infer the main use, but exclusions and alternatives are left implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.