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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description adds meaningful behavioral context: per-call pricing (¥0.0125/次), billing behavior (空响应不计费 - empty responses not billed), and a ~20k token reliability ceiling. The cost disclosure usefully contextualizes the destructiveHint=true (financial consumption). No contradiction with annotations.

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?

A single dense paragraph with no filler: each sentence earns its place (function → cost → use cases → input limits). The core purpose is front-loaded before the cost and usage detail. Slightly packed, but nothing is redundant with the schema.

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 simple 2-parameter tool with no output schema, the description covers the essentials: function, cost model, use cases, and input constraints. The 'OpenAI 兼容' framing implicitly conveys the standard chat-completion response shape. Minor gaps: it doesn't explicitly describe the return format or explain why destructiveHint=true, but these are partially mitigated by the OpenAI-compatibility convention and cost disclosure.

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 both 'model' and 'messages' are already documented in the schema. The description confirms the default model (matching the schema) and reinforces the OpenAI-format/multi-turn semantics of 'messages'. It adds token-limit guidance for content sizing, which is genuinely useful, but the schema carries the heavy lifting — baseline 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 states a specific verb ('调用' - invoke/call) and resource ('EveryInfra 的 AI 文本补全' - AI text completion), with the OpenAI-compatible framing and default model clearly identified. It lists concrete use cases (摘要、翻译、情绪打标、主题分类、结构化抽取) that distinguish it from siblings like everyinfra_search and everyinfra_solve_captcha without needing to inspect their schemas.

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 gives clear usage context: '适合...批量任务' (suitable for batch tasks) with specific task types, plus an input-sizing guideline ('更长文档请先切块' - chunk longer documents). It doesn't explicitly name alternatives to exclude, but the sibling tools are functionally distinct enough that the implied usage is unambiguous.

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