okx_agent_feedback

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

With no annotations provided, the description fully discloses behavioral traits: declares [L:READ] and '风险：READ — 只写日志，Agent 可随时调用' (risk: READ - only logs, Agent can call anytime), indicating no side effects. Also specifies '鉴权：PUBLIC — 无需 API Key' and return size '微小 ~200B'. No contradictions.

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?

Description is well-structured with sections (功能, 场景, 关键词, 参数, 鉴权, 风险, 返回量, 关联), but it is somewhat verbose. Every section serves a purpose, but could be more concise. Front-loads key info with [L:READ] and CAT, which helps.

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?

Given the tool has 5 parameters (all required), no enums, no output schema, and no annotations, the description covers function, usage scenarios, parameter descriptions, authentication, risk, return size, and follow-up process. It is fully complete for the agent to understand when and how to use it.

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 baseline is 3. The description adds brief explanations for each parameter (e.g., '一句话标题', '你做了什么操作'), which adds some meaning beyond schema labels. However, it does not provide detailed formatting or examples.

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?

Description clearly states the tool's purpose: submitting feedback about MCP tool usage pain points. It specifies the verb '提交' (submit) and resource '使用反馈' (usage feedback). It distinguishes itself from sibling tools by explicitly listing scenarios when to use it, such as multi-step issues, parameter trial errors, or inability to find tools.

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?

Description provides explicit scenarios for when to use the tool: when encountering tedious multi-step operations, parameter trial error, unknown call order, can't find tools, or need to supplement with manual calculations. It lacks explicit 'when not to use' or alternatives, but the positive conditions are clear and specific.

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