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

With no annotations provided, the description carries the full burden. It discloses a key behavioral trait: '在不扣费的情况下' (without charging), informing the agent this operation does not incur cost. It also uses '预估' (estimate), implying it does not execute an API call. These are valuable, non-obvious behaviors beyond what the schema shows. It doesn't address response format, but core safety aspects are covered.

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 description is two short sentences, immediately stating the primary action and cost nuance, followed by the usage context. Every word earns its place; there is no ambiguity. The transparency about non-charging is front-loaded. This is highly concise yet complete for the tool's scope.

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 tool of this simplicity (3 parameters, no nested objects) and no output schema, the description provides adequate operational context: it states the tool's exact purpose, the key behavioral guarantee (no deduction), and a concrete invocation scenario (budget gate). It could mention expected return value (USD number), but the description already says '费用（USD）' which strongly implies a USD amount. Overall, it suffices.

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 input schema already documents all three parameters (prompt, asset_id, max_tokens) with adequate descriptions. The tool description adds no parameter semantics beyond pointing to the estimate context. Per the baseline rule, when schema covers everything, a 3 is appropriate.

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 clearly states the tool's verb and resource: '预估一次 AI 调用的费用（USD）' (estimate the cost of one AI call in USD). It also distinguishes itself from siblings by clarifying it is a budget gate ('预算闸门'), positioning it against ai_request which likely executes calls. This is specific and unambiguous.

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 description explicitly says '调用前用它做预算闸门' (use it as a budget gate before calling), which gives a clear when-to-use context. It does not explicitly name ai_request as an alternative, but the '调用前' (before calling) implies the intended counterpart. The guidance is strong though not fully exhaustive.

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