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

With no annotations provided, the description carries the full burden and largely meets it: it declares the tool is advisory/read-only ('reads the command, it does not run it'), that it returns one of three dispositions, and that intent can be supplied. It does not cover auth requirements, latency, or failure behavior.

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 tight sentences: the trigger, the enumerated risk categories, the intent hint, and the scope caveat. Front-loaded and free of padding, though the opening 'Free sample.' is promotional rather than informative and does not earn its place.

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 two-parameter classification gate with no output schema, the description covers trigger, scope, non-execution, and the possible dispositions, which is enough for an agent to call it correctly. Minor gaps remain on response shape details and any limits on command length or rate.

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 coverage is 100%, so the baseline is 3, and the description adds genuine value by advising when to supply 'intent' ('Pass the human intent when you know it'), implying it improves the judgment rather than being required. It does not add format or syntax detail beyond the 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?

States a concrete verb and resource: it asks whether to 'allow, review or block' a shell command before an agent runs it, and enumerates the risk categories it judges (root deletion, download and run, privilege escalation, secret exfiltration). The 'Not a sandbox' clause sharpens the boundary, but it does not distinguish this gate from the sibling verdict_firewall/verdict_guard/mcp_vet tools.

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?

Gives a clear trigger ('Before a coding agent runs a shell command') and concrete motivating cases for invoking it. It also rules out a likely mis-assumption ('Not a sandbox: it reads the command, it does not run it'). It stops short of naming when to prefer a sibling tool or any exclusions beyond that.

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