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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-structured context: results come from a '真实算法引擎' and are not LLM-generated ('非大模型生成'), which tells the agent the output is deterministic/computed and should be trusted as such — a meaningful behavioral disclosure. It still does not explain how multi-round state is carried or what happens if 'round' is omitted.

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?

Three compact segments — bracketed label, trigger condition, return value — with the purpose front-loaded and only the parenthetical provenance clause as extra weight. The bracketed title largely duplicates the annotation title, which is minor waste but not harmful.

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 does state the return ('追问答复'), which is the key gap filled. For a 4-parameter, multi-round tool with no annotations gap, though, it should say how rounds are sequenced, whether prior rounds must be supplied, and whether a report step follows; those are left unstated.

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 each parameter already carries a description ('轮次', '标题', '摘要', '追问问题'). The description's '多轮' loosely maps to the 'round' parameter and '已录入的证据' to title/abstract, but it adds no format, default, or sequencing guidance beyond the schema. Baseline 3 applies.

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 verb and resource: continue questioning ('继续追问') already-recorded evidence and making causal judgments ('做因果判断'), plus it states the return value ('追问答复'). This distinguishes it from intake/report siblings implicitly, but no sibling is named in the text, so an agent must infer that act_decision_intake comes first.

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 phrase '已录入的证据' implies a precondition — evidence must already exist before this tool is used — and '多轮' implies it is called repeatedly. However, there is no explicit when-not guidance, no statement of how it relates to act_decision_intake or act_decision_report, and no indication of what to do on the first round.

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