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

No annotations are provided, so the description carries the burden and largely meets it: it discloses the two-step call pattern, what the second step returns (摘要 + 小标题清单), and critically that 正文 is NOT returned. It does not discuss auth, rate limits, or pagination, so a small gap remains.

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?

Front-loads what it does, then intent-based triggers, then the two-step mechanics, with no wasted clauses. The ★ markers and mixed parenthetical asides make it dense, but every sentence adds actionable content rather than padding.

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 and three fully-documented parameters, the description supplies the missing return-value context (abstract + section skeleton, no body) and the two-call workflow. Nothing essential for correct invocation is absent, though it could say more about the shape of the entry list returned in step one.

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 100%, so the baseline is 3, but the description goes further by explaining how q and key relate as a two-step workflow (先传 q 列条目，再回传 key) — information the schema documents per-parameter but not as a sequence. It also clarifies the empty-q behavior for each parameter's role.

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 verb (检索) and resource (本站「教程类」内容) and enumerates the seven content types it covers (办事指南、流程、证据清单、问答、判例、模板、合同), which lets an agent distinguish it in domain from search_articles/search_law. However, it never names a sibling tool, so differentiation is by content domain rather than explicit routing.

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?

Gives explicit trigger phrases (「怎么办理、要带什么材料、走哪些步骤、有没有范本/清单、类似案子怎么判」), an explicit prioritization rule for procedural/material questions, and a default for the kind enum (不确定就用 guide). This is as actionable as usage guidance gets.

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