sentinel_safe_exec

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

With no annotations, the description carries the full burden and does disclose meaningful enforcement behavior: AST inspection, command-chaining prevention, timeout enforcement, and automated DLP secret redaction of output. It does not say what happens when a command is blocked, how failures/exit codes are surfaced, or whether redaction alters stderr, leaving some behavioral gaps.

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?

A single sentence with the imperative verb front-loaded and three parallel enforcement clauses, each of which adds distinct information about the sandbox's guarantees. No filler, no restatement of the tool name, nothing to trim.

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?

No annotations and no output schema exist, so the description should ideally describe return shape (exit code, stdout/stderr, redaction effects) and failure modes. It covers the security envelope well but leaves the agent guessing about results and error behavior for a relatively complex execution tool.

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% – cwd, command, and timeoutMs are each documented in the schema, including the default timeout and the sandbox-root constraint on cwd. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ('Execute shell commands') plus the execution environment ('AST-inspected security sandbox'), so the agent knows exactly what the tool does. It does not explicitly differentiate itself from siblings like sentinel_policy_check or sentinel_audit_inspect, but the sandboxed-exec framing is distinct enough from fs/fetch siblings to be actionable.

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 never states when to use this tool versus alternatives such as sentinel_policy_check, nor any preconditions (e.g., that commands must pass policy, or when to prefer sentinel_safe_fs for file work). Usage is only inferable from the verb 'Execute shell commands' and the tool name, with no exclusions or routing guidance.

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