按组装载工具（含 nano 极简档）

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

Beyond the annotations, the description explicitly discloses that this tool changes target state and may occupy shared resources like debug/serial/Keil instances, assigns a medium risk level, and notes that rollback is possible. It also discloses the client-side caching behavior and the need to re-pull tools/list, providing valuable operational 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 compact and front-loaded with the core action, then covers syntax, caching behavior, and risk. The bracketed parameter/example/risk sections are efficient, though the empty call example '{}' adds little value and the risk note is somewhat verbose.

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 tool with two optional parameters)Skip the redundant text, the description provides all needed context: valid group values, unload semantics, client caching caveat, risk profile, and rollback note. An output schema exists, so return-value details are not the description's burden; the tool can be invoked correctly based on this description alone.

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 0%, so the description must compensate. It does: it explains valid values for group (single, comma-separated, all, nano) and gives unload=true the meaning of retracting/collapsing the loaded group. It does not fully explore combinations like unload with all/nano, but the essential semantics are present.

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 action: load the specified group into the active tool surface, with unload=true to retract. It clearly distinguishes the tool's scope by explaining valid group values (single, comma-separated, all, nano) and the unload behavior, making its purpose unambiguous.

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 implies when to use it (loading/unloading tool groups) and provides a practical follow-up action when the client still reports unknown tools, including the client caching caveat. However, it does not explicitly state when to prefer this over sibling tools like tools_groups or list_tools, nor does it name exclusions or alternatives.

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