Jev Risk Score

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

Annotations mark it read-only and open-world; the description adds non-obvious behavioral limits: it is advisory only and explicitly subordinate to tests, evidence, reasoning, and review. It also states return categories, but does not describe model/state handling or output format beyond the category list.

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 tightly constructed sentences, front-loaded with the usage directive and return categories, then the critical limitation. No filler.

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?

Purpose, usage boundaries, and return categories are covered, which matters given the absence of an output schema. However, with 33% schema coverage and optional model/question parameters, the description leaves parameter-level guidance to the schema and does not compensate for the gaps.

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 only 33%: state has a description, model and question do not. The description does not compensate by explaining these parameters, the anyOf state formats, or question semantics, so it adds little 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 the tool returns a risk score with four categories and frames it as an advisory second opinion. Its role is distinguishable from decision/gate siblings by the non-authorization and non-override framing, though no sibling is named explicitly.

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?

Specifies when to use it: for consequential or ambiguous-risk changes after inspecting context. It also sets when-not boundaries: never authorization and never overrides tests, deterministic evidence, primary-model reasoning, or review. Alternatives are implied but not named.

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