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

With no annotations supplied, the description carries the burden and does solid work: it declares the operation is a read-only evaluation with no side effects and spells out the return contract { passed: boolean, reason: string }. It leaves undisclosed what happens when passed=false (does the caller abstain, retry, or escalate?), which is the key behavioral question for a gate.

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?

Four short sentences, front-loaded with the standardized-gate marker, then purpose, then timing, then contract. Nothing is wasted, though the unexplained jargon term "NatATL" costs the reader a beat and the bracketed header is somewhat ceremonial.

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?

There is no output schema and the description compensates by stating the return shape, so the basic contract is covered. However, for a gate tool with one undocumented parameter and no guidance on interpreting a failed verdict, an agent still lacks what it needs to act on a negative result.

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 50%, and the description adds nothing parameter-level: it only restates actionProposal as a "proposed action or command." The second parameter, isPlanningOnly, is undocumented in both the schema and the description, which is a meaningful gap for a gate that may treat planning text differently from executable commands.

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 (verify) plus the resource (a proposed action or command) and names the exact check families: SQLi, OS command injection, and NatATL bounds. No sibling in the provided list (vault_*, session_*, map_*, sidecar_*) is a safety gate, so the tool is unambiguously distinguishable.

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?

"Call BEFORE executing any external shell or DB commands" gives explicit invocation timing tied to a concrete trigger condition. It stops short of exclusions or alternatives (e.g., what to do for non-shell/non-DB actions, or whether planning-only work needs the gate), so it is clear context without full routing guidance.

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