jev_guard

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the result is advisory and non-intercepting, and that evaluation is layered (deterministic regex then probabilistic unless reflex_only), plus the offline/runtime implication of reflex_only. It stops short of describing what the screening produces (score, verdict, findings) or latency/cost characteristics, which is a meaningful gap for a tool with no output schema.

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?

Two sentences, front-loaded with the core purpose and capped by the non-interception guarantee. No filler, and the parenthetical mode switch is placed where it is needed.

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 tool with no annotations and no output schema, the description covers the input side and the safety posture but never explains what the agent receives back or how to act on it. The core purpose is clear, yet the informational contract of the call is left implicit.

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%, so all three parameters are already documented, and the description largely mirrors that (reflex_only's offline meaning is already in the schema). It adds no syntax, format, or example for 'command' or 'context', so it sits at the baseline.

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 ('risk screening for a shell command') and specifies the two evaluation layers, which is more than a restatement of the name. It does not explicitly differentiate itself from siblings like jev_route or jev_arbitrate, so an agent still has to infer the boundary.

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 phrase 'advisory risk screening' and 'Does not intercept host execution' imply a pre-flight, non-blocking checking context, and the reflex_only clause hints at an offline mode. However, there is no explicit when-to-use/when-not guidance and no reference to the sibling tools for alternative needs.

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