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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds only 'multi-turn' and 'RETURNS: 追问答复', leaving the key behavioral question unanswered: is conversation history held server-side by this tool, or must the caller replay the card via title/abstract/round on each turn? That ambiguity matters for a read-only multi-turn tool.

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?

The pipe-delimited USE WHEN / ALIASES / RETURNS header is front-loaded and easy to scan, with no filler prose. It does duplicate the title string unnecessarily.

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 a return value described only as '追问答复', plus no definition of what an evidence card is or how turns are chained, an agent cannot confidently construct a correct multi-turn call. For a stateful, 4-parameter tool this is a real gap.

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 100%, so the baseline is 3. However, the schema labels are bare one-word glosses (轮次, 标题, 摘要, 追问问题) that convey almost no meaning, and the description does nothing to explain that title/abstract form the evidence-card context or what 'round' controls.

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 action (multi-turn follow-up Q&A) on a specific resource (an evidence card, scoped to causal judgement), which is more precise than the sibling names evidence_intake / evidence_report. It does not explicitly contrast itself with those siblings, so it stops short of a 5.

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 'USE WHEN: multi-turn follow-up on an evidence card' clause gives a real trigger condition, which is better than nothing. But it never says what to do first (presumably evidence_intake must have produced the card), what happens when there is no prior card, or when to prefer evidence_report instead.

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