jev_gate_action

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

Annotations already mark it read-only and open-world, and the description goes beyond that by disclosing that Jev is not hardened against adversarial text and that action/context can be written to influence the result. It also reveals the deterministic-policy-in-code behavior and translates confirm/block into required agent behavior. No contradiction with annotations.

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?

The description is front-loaded with the core purpose, then the security caveat, then usage timing, parameter guidance, and output interpretation in a sensible order. Although it is longer than a one-line definition, the gating decision is complex enough that the length is justified and every sentence earns 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?

Given an output schema exists and the input schema covers all parameters, the description supplies the missing behavioral context: when to call it, how to phrase action and user_request, what confirm/block instruct the agent to do, and important security caveats. An agent has enough information to invoke it correctly without additional documentation.

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 the baseline is 3. The description reinforces how to pass action concretely and user_request in the user's own words, but these largely restate the schema's field descriptions. It adds no substantive detail about context or thresholds beyond what the schema already provides.

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?

Description names a specific verb-path: an advisory pre-flight check that judges an action before execution and returns allow/confirm/block from a deterministic policy. It clearly defines what the tool evaluates: destructiveness, outward-facingness, scope, credential impact, and blast radius. This makes it distinct from the sibling jev_* tools, which are evaluation/ranking/verification helpers rather than a gating policy.

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?

Explicitly says to use it just before something that cannot be cheaply undone and gives concrete categories: file deletion/overwrite, git history rewrites, installs, deploys, messages, spending money, and external systems. It also states a when-not: it is not a security boundary and must never be relied on to contain untrusted input or replace a real permission check. It does not name sibling alternatives, so it stops short of a full 5.

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