Run shell command

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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the danger profile is covered. The description adds value beyond that with the two environment gating conditions and the cwd restriction, though it omits timeout default behavior and output truncation semantics.

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?

Three dense sentences with the core action front-loaded and prerequisites following. Every sentence carries information and there is no filler.

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 7-parameter tool with 0% schema coverage and no output schema, the description leaves too much unexplained: six of seven parameters, the enum runner choices, and the return shape (stdout/stderr/exit code) are all absent. Annotations cover safety but not the invocation details an agent needs.

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 carry the burden, but it only implicitly touches cwd ('specified working directory') and command. The runner enum, deviceId/deviceName, timeoutMs, and maxOutputBytes parameters are never explained anywhere.

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 gives a specific verb and resource ('Run one shell command') plus the working-directory scope, so the agent knows exactly what the call does. It stops short of distinguishing this from long-running siblings like process_start or adb_shell, which a 'one shell command' phrasing only implies rather than states.

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?

It states gating prerequisites (RACCOON_ENABLE_SHELL=1, and RACCOON_FILESYSTEM_UNRESTRICTED=1 for absolute cwd), which is real context. However it gives no when-to-use-this-vs-alternatives guidance against the many process/adb siblings, so selection is left to inference.

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