Execute Android system shell commands through an authorized Shizuku service, running as shell (UID 2000) or root when explicitly granted.
Execute /system/bin/sh in an explicitly-authorized Shizuku UserService. It runs as shell UID 2000, or root only if the user explicitly started Shizuku as root.
| Name | Required | Description | Default |
|---|---|---|---|
| stdin | No | ||
| script | Yes | ||
| workdir | No | ||
| timeoutMs | No |
Changes observed during successful MCP inspections.
v0.6.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as destructive and non-idempotent. The description adds useful behavioral context beyond that: it runs as UID 2000 and only gains root if the user explicitly started Shizuku as root. It also clarifies that explicit authorization is required, which is valuable for an agent deciding whether to invoke it.
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?
Two focused sentences convey the core action, authorization model, and privilege behavior with no filler. The most important security boundary (shell UID vs root) is clearly stated.
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?
The description covers the essential execution model and privilege context, but it does not mention return behavior, stdout/stderr, exit codes, or how stdin/timeout/workdir affect execution. With no output schema, an agent still has to guess what the tool returns after running a script.
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%, and the description does not explain any of the four parameters. Although names like script, stdin, workdir, and timeoutMs are somewhat self-explanatory, the description provides no extra guidance on how they interact or what values are expected, so the schema's lack of descriptions is not compensated.
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 names a specific action ('Execute /system/bin/sh') and a specific resource/environment ('explicitly-authorized Shizuku UserService'). The UID/root clarification also distinguishes this from the plain android_shell sibling, so an agent can tell them apart.
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 this tool: when an authorized Shizuku shell is needed and potentially root-level execution is acceptable. However, it does not explicitly name alternatives like android_shell or state conditions under which one should prefer one over the other.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.