shell_exec

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

Annotations declare destructiveHint=true and readOnlyHint=false, and openWorldHint=true, covering the safety profile. The description itself adds little behavioral context beyond what annotations convey — it doesn't mention that arbitrary commands could have side effects, require root, or block on long-running commands. However, it doesn't contradict the annotations, and the destructiveHint annotation does substantial work here, so the description's minimal addition is acceptable but not rich.

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 compact sentences with zero waste. The first states the core operation, and the second adds positioning guidance. Front-loaded with the action verb. Perfectly sized for a catch-all tool that needs to convey purpose and scope without unnecessary verbosity.

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?

Despite having an output schema, the description is brief but sufficient for a general-purpose escape-hatch tool: it conveys purpose, scope, and usage positioning. Given its catch-all nature, exhaustive behavioral documentation isn't feasible, and the high schema coverage plus output schema relieve the description of return-value and parameter detail burdens. It's adequate for the tool's role.

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 100%, meaning both parameters (serial and command) have descriptions in the schema. The description adds limited value beyond the schema — it doesn't explain the serial parameter's optionality semantics (capturing 'the device' but serial being optional), nor does it explain output format. Baseline 3 is appropriate since the schema fully documents parameters.

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 clearly states it executes an ADB shell command on the device and returns output. The verb 'Execute' plus the specific resource ('ADB shell command') make the purpose clear, and the second sentence ('Use this for any device operation not covered by other tools') helps position it against the large sibling set. It doesn't name specific sibling alternatives, but 'not covered by other tools' explicitly signals its generalist fallback role.

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 explicitly states 'Use this for any device operation not covered by other tools,' which gives clear when-to-use guidance and implicitly establishes when NOT to use it (when a specialized sibling exists). This is effective for a fallback/catch-all tool among 48 siblings, though it could be stronger by naming a couple of concrete examples of what operations fit here.

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