复位目标

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

The description goes far beyond the annotations (destructiveHint=true, readOnlyHint=false) by disclosing the exact post-reset state (stopped at reset vector), the need for an explicit run, the get_status result, and the irreversible nature (rewrites flash/memory or restarts Keil). It also explains the run_after parameter's behavior.

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 structured with bold headers (行为说明, 参数, 调用示例, 风险) and front-loads the core purpose and critical behavioral change. Every sentence adds value, and the risk warning is clearly highlighted.

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 destructive, irreversible operation, the description covers the reset behavior, return fields (state_after_reset, stopped_after_reset), parameter semantics, call example, and risk warning. Even though an output schema exists, the description adds critical context about the return values and post-reset state.

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 0%, so the description fully compensates by explaining run_after: optional, default false, and its purpose (auto-run after reset). The example {} clarifies that no parameters are required.

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 states a specific action (reset target MCU), the resource (target MCU), and clarifies that variables return to initial values while breakpoints are preserved. It clearly distinguishes the purpose from siblings like run or stop.

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?

Explicitly explains that after reset the target stops at the reset vector and requires a subsequent run call, and notes run_after for auto-run scenarios. It doesn't explicitly list alternatives for when not to use it, but the context (e.g., '重新跑一遍看串口输出') provides clear usage guidance.

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