Check trend items you plan to publish for relevance and score supplemental search entries in one call; recheck items scoring below 0.6 before writing.
发布前自检：关联度（方向性覆盖）+ 补搜条目打分，一次调用。 硬约束：量的是准备发布的条目（bucket=core 或显式 entries），不要传全池；关键词 ≤ 8；补搜条目 ≤ 10 且必须带 url；<0.6 必须重查后再写。
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| bucket | No | core | |
| domain | No | broad | |
| run_id | No | ||
| entries | No | ||
| external | No | ||
| keywords | No |
Changes observed during successful MCP inspections.
v0.3.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It usefully reveals the score gate behavior ('<0.6 must re-verify before writing') and the scoping constraints, which is genuine behavioral value. But it never states whether the call mutates state or is a safe read, nor what it returns, leaving important behavior inferred rather than stated.
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 tightly packed sentences: the purpose is front-loaded, then the hard constraints follow in a labeled clause. Very little waste, though the compressed constraint block assumes prior familiarity with the surrounding workflow vocabulary.
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?
With no annotations, no output schema, and 7 params at 0% schema coverage, the description should carry heavy load. It covers the operationally critical constraints well but omits query/domain/run_id semantics and any hint of the response shape, leaving the definition only partially complete for a tool this parameterized.
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. It does explain bucket (bucket=core), entries (explicit entries), keywords (≤ 8), and the supplementary/external list (≤ 10, must include url). But query, domain, and run_id are left entirely undocumented, so only part of the 7-parameter surface gains meaning.
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 names a specific operation (发布前自检 = pre-publication self-check) and enumerates its two outputs: relevance/directional coverage and scoring of supplementary entries. It clearly reads as a measurement/validation tool, but it never distinguishes itself from the sibling tools radar_scan or radar_pack, so an agent cannot tell them apart without external context.
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?
It gives concrete usage context (pre-publication) and explicit exclusions such as 'measure the entries about to be published (bucket=core or explicit entries), do not pass the whole pool'. These are real when/when-not constraints. However, it does not name an alternative tool or state which situations should route to radar_scan/radar_pack instead, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.