computer.run_command

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

No annotations are provided, so the description carries the full transparency burden. It discloses output truncation, credential redaction, and allowlist enforcement, which are important behavioral traits beyond what the schema shows. It does not explicitly state destructiveness or side effects, but 'run a shell command' plus confirm=true implies mutating capability.

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 a single dense sentence that front-loads the action and packs constraints efficiently. Every clause contributes new information, with no filler or repetition.

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 3-parameter tool with no annotations and no output schema, the description covers the critical invocation constraints: allowlist dependency, the need for confirm=true, and output behavior. It omits timeout semantics and error/exit-code format, but those are secondary for selecting and calling the tool correctly.

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 compensate. It adds meaningful semantics for confirm ('requires confirm=true') and clarifies command scope via the allowlist, but it never mentions timeout_s or how it behaves. The schema provides type/default, leaving timeout semantics still ambiguous.

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.' No sibling tool duplicates this capability, and the added context about the allowlist and confirmation requirement further clarifies what the tool does.

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 gives concrete usage conditions: the security allowlist applies, output is truncated and credential-redacted, and confirm=true is required. It points to computer.backend_status for allowlist details, though it does not explicitly name alternative tools or when not to use this one.

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