r2_disassemble

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

该工具没有 annotations，描述承担了行为披露的责任。它说明了内部使用 'pd' 命令、要求确认目标文件绝对路径、禁止捏造路径或命令结果，并提醒 session_id 不再使用时必须关闭，这些是超出 schema 的有用行为信息。但未说明是否需要先打开文件、是否依赖已激活的 r2 会话，副作用披露仍不完整。

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?

核心功能、触发场景、使用规则分节明确，且功能信息前置。但英文 “Use when” 列表与中文“触发场景”内容高度重复，存在冗余，整体不够精炼。

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?

对于 3 参数、无输出 schema 的工具，描述已覆盖功能、使用时机、输入前置条件和资源清理规则，足够支持基本调用。未说明返回格式或如何获取 session，但“显示汇编指令”的语义已隐含输出形态，影响不大。

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?

输入 schema 覆盖率为 100%，session_id、address、lines 三个参数都已有清晰描述，description 未逐参数补充额外语义。它只是复述“指定地址”和使用 pd 命令，未超出 schema 已提供的信息，因此保持在基线 3 分。

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?

描述明确说明“反汇编指定地址的代码”并指出使用 'pd' 命令显示汇编指令，动作和对象清晰。但没有显式与 r2_run_command、r2_decompile_function 等兄弟工具区分，触发场景中还混入“radare2命令执行”这类宽泛表述，略微削弱辨识度。

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?

有专门的触发场景说明：“当用户询问二进制逆向分析、反汇编、漏洞挖掘、radare2命令执行、调试相关问题时，必须优先调用此工具”，给出了明确的 when-to-use。但没有提供 when-not-to-use 或与替代工具的对比，且“radare2命令执行”范围过宽，可能误导代理优先选择此工具而非 r2_run_command。

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