后退

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

The description discloses the basic behavior (browser back) but does not mention any side effects, edge cases (e.g., exceeding history length), or error handling. The annotation readOnlyHint=false is consistent with the action's state-changing nature, and no contradiction exists. However, richer detail on behavior would improve transparency.

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 a single, concise sentence that exactly conveys the tool's function without any unnecessary words or repetition. It is well-structured and front-loaded with the core action.

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 simplicity of the tool and the presence of an output schema (not shown but indicated by 'Has output schema: true'), the description is complete. It does not need to explain return values, and all essential information for using the tool is present.

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?

The description adds no extra meaning beyond the schema. The schema already provides Chinese descriptions for both 'steps' and 'tab_id' (e.g., '后退步数' and '标签页 id，省略时用最新标签页'). Since schema coverage is 100%, the baseline of 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 action: '在标签页中执行浏览器后退' (execute browser back in the tab). The tool name 'navigate_back' is unambiguous, and the action is simple and specific, leaving no room for misinterpretation.

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 provides only a direct action statement without explicitly contrasting with sibling tools like 'navigate_forward' or 'navigate'. While the purpose is clear, the description does not guide on when to prefer this tool over alternatives, though the simplicity may not require extensive guidance.

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