computer_bash

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that the command runs unsandboxed as the desktop user, that /bin/sh or cmd.exe is used so bash-only syntax may fail, and that non-zero exits are returned in data.exitCode rather than as tool errors. This is exactly the behavioral context an agent needs for a dangerous tool.

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 tight and well-organized: a one-line purpose, a danger warning, exit-code semantics, then parameter and return docs. Every sentence contributes essential information, and the most safety-critical points are front-loaded.

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 risky shell-execution tool with no annotations, the description is complete. It covers safety, shell flavor, exit-code behavior, timeout defaults, parameter sourcing, and the return envelope. An agent has everything needed to invoke it correctly without guessing.

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%, but the description documents all three parameters meaningfully. It explains serialno comes from list_devices, command is the shell command, and timeout is in seconds with the critical clarification that omitting it or using 0 applies the server's 120s default. This adds real value beyond the bare schema.

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 verb and resource: 'Run a shell command on the host machine that owns this device.' This clearly distinguishes computer_bash from on-device tools like mobile_bash and from higher-level computer interaction tools, giving an agent enough to select it correctly.

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 provides clear context for when this tool is appropriate: arbitrary shell access on the host machine, with a strong warning to treat it as shell access. It does not explicitly name alternatives or exclusions, but the 'host machine' scope and danger framing make the intended use unambiguous.

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