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

Annotations already declare idempotentHint=true and destructiveHint=false; the description adds meaningful context beyond them: login is required, the call is a pure computation that no longer invokes the model, and it does not move or create funds ('不创建资金'). That last point is important for an agent reasoning about financial safety. It stops short of describing what the returned split looks like.

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?

Telegraphic but dense: auth requirement first, then the operation, then the expiry rule and the no-funds guarantee. No wasted sentences, though the semicolon-fragment style makes it slightly harder to parse than flowing prose.

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?

For a two-parameter preview tool with no output schema, the definition covers auth, behavior, idempotency context and financial safety. It still leaves the return structure ('返回实际分账') and the origin of quoteToken unexplained, which an agent needs to chain this correctly after a quote call.

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 carry the load. It does explain that originalUnitAmountCents is the original price in cents and that quoteToken defines the valid scope, which is real added meaning. But the provenance and lifetime of quoteToken (presumably issued by the quote step) and the bounds of the amount are left unstated.

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 states a specific action (preview/derive the actual split from an original price) scoped to a quoteToken, and distinguishes it from the quote step by saying no model call happens ('不再调模型'). An agent can tell this apart from quote_network_bounty or claim_network_bounty, though the sibling is not named explicitly.

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?

'过期/条件变化须重报' gives a clear when-not rule: if the quote has expired or conditions changed, go back and re-quote. '登录' signals an auth prerequisite. However, it never names the alternative tool (quote_network_bounty) or states the normal precondition that a fresh quoteToken must already exist, so the routing guidance is implied rather than explicit.

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