全速运行

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

Adds substantial behavior beyond the annotations (readOnlyHint=false, idempotentHint=false): the async message pileup that corrupts memory/register reads while running, the unreliable dirty PC value in run's return, the halt-type debug nature where peripherals stall while the debugger is connected, and the UVSOCK async message push. These are critical, non-obvious behaviors that annotations cannot express. No contradiction with annotations — mutation semantics match readOnlyHint=false.

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?

Front-loaded with the core purpose, then caveats, then the free-run guidance. Each section carries genuinely useful information for correct use. It is on the verbose side — the 看不到现象 philosophical explanation of halt-type debugging could be tightened — but for a debug tool with these non-obvious behaviors, the length is largely justified and every sentence earns its place.

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?

Complete for a tool of this complexity: output schema covers return values, annotations cover the safety profile, and the description thoroughly covers the behavioral gotchas (async pileup, dirty PC, halt-type semantics, free-run procedure) plus the medium risk and call example. Nothing an agent needs to call it correctly is missing.

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?

Zero parameters with 100% schema coverage (trivially, an empty schema), so the baseline of 4 applies. The description explicitly notes 无（直接调用） and shows the empty call example, confirming no parameters need explanation. Nothing more is needed.

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?

States a specific action — 让目标 MCU 全速运行（启动执行） — with a clear resource (target MCU) and verb (full-speed run/start execution). It implicitly distinguishes itself from siblings like step (single-step) and run_timeout (timed run), and the title 全速运行 reinforces the purpose. Nothing is vague or tautological.

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?

Provides strong contextual guidance: warns that reading memory/registers after run will fail and that stop is required first, and instructs using get_current_location to verify PC position instead of trusting run's returned stop info, plus exit_debug for free-running. However, it never explicitly routes to named siblings (e.g., 'use step for single-stepping' or 'use run_timeout for bounded runs'), so the when-to-use vs alternative guidance is rich but not fully explicit.

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