driftguard_safety_check

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

No annotations are supplied, so the description carries the full behavioral burden. It discloses one important trait — that the tool blocks destructive commands and what classes it catches — but it is ambiguous about what 'bloccando' means operationally: does it prevent execution, or merely return a verdict, and what result shape (risk level, allow/deny) does the caller get? No mention of failure modes, latency or whether it inspects only the literal string versus expanded shell 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?

A single well-formed sentence that front-loads the action and timing, then backs it with concrete examples. Nothing is wasted, though the parenthetical example list is the only thing preventing a 5.

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 one-parameter pre-flight check with no output schema, the description covers what it inspects but not what it returns or how the agent should react to a block versus a pass. The absence of an output schema makes that omission more consequential, so the definition is adequate but incomplete for correct invocation handling.

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?

There is a single required parameter with 100% schema description coverage ('Il comando shell che l'agente intende eseguire'), so the schema already does the work. The description adds indirect meaning by listing the destructive patterns the input is screened against, hinting at expected format, but it adds no syntax or edge-case guidance beyond that.

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 ('valuta preventivamente il rischio di un comando shell') plus a concrete scope: blocking destructive commands, with named categories (rm -rf /, drop database, key exposure, fork bomb). This clearly separates it from generic sibling utilities. It stops short of naming overlapping siblings such as driftguard_policy_check, driftguard_dry_run_command or driftguard_scan_secrets, so the boundary requires inference.

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 clear timing context ('prima di eseguirlo'), which implies the when-to-use condition: run this before executing a shell command. However, with several adjacent siblings in the same family (policy_check, dry_run_command, scan_secrets, audit_dependencies), no exclusion or alternative routing is offered, leaving the agent to guess which check applies.

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