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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial semantics beyond them: anonymous is an ipHash-folded lower bound that must not be fabricated into identities, named requires logged-in viewers with unidentifiable accounts downgraded to anonymous, bot traffic (~41%) and self-views are pre-filtered, empty returns are statistically normal (2~12 named visitors/day), and named.length ≠ namedCount implies truncated=true. No contradiction with annotations.

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?

Despite its length, the text is organized into scannable labeled sections (需要登录/何时用, 组合链, 口径/坑) and front-loaded with the use case. Every sentence prevents a concrete failure mode — fabrication, miscounting totals, parameter retry loops, stale social outreach — so there is no padding; the density justifies the size.

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 output schema, the description carries the full burden of return semantics, and it delivers: named[].viewerId, named[].what, namedCount, anonymous, and truncated are all defined well enough to execute the composition chain correctly. The only omitted detail is the exact response envelope shape, which is minor given the operational fields are all specified.

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 covers both params at 100% with defaults and ranges, so the baseline is 3. The description adds operational meaning beyond the schema: the social rationale for the 7-day default, the guarantee that namedCount is always the true window total regardless of limit, and a warning not to probe params when empty is the norm. This is meaningful additive value, though the schema still does the heavy lifting.

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 concrete verb and resource: listing recent viewers merged from three streams (产品被浏览 / 主页被浏览 / 需求作者页被点开), with explicit trigger phrasings (「最近有人关注我吗」「谁看了我的产品」) plus the non-obvious use case of finding a conversation starter. This sharply distinguishes it from the ~120 sibling list tools without needing to open the schema.

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?

An explicit 【何时用】 section states trigger conditions and the proactive-chat use case. The 【组合链】 section routes to complementary tools conditionally (get_relationship first, follow_creator if not ready to disturb, get_creator → start_conversation after), and pitfalls give when-not guidance: don't retry with changed params on empty returns, don't stretch the window because two-week-old views make outreach awkward.

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