Jev patch review

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

Annotations already declare readOnlyHint and destructiveHint=false, lowering the burden on the description. The description adds meaningful behavioral context by saying the patch is not applied and that composite weights live in code, which explains why the scoring logic is not fully exposed. There is no contradiction with the 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 short, front-loaded with the main action, and every sentence earns its place. The phrase 'plus noul safe_to_apply' is awkward and slightly unclear, but it does not significantly hurt structure.

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?

The description gives enough orientation for a basic required-parameter call and lists key output dimensions including safe_to_apply. However, with no output schema and 11 parameters, it leaves the return payload shape and the meaning of several optional parameters to inference.

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 27%, and the description adds little beyond mapping 'diff' and 'request' to inputs. It provides no meaning for model, tests, review_at, auto_accept, truncated, changed_files, context_version, evidence_complete, or repository_context, so the low coverage burden is not compensated.

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?

The description uses a specific verb and resource: 'Score a proposed diff against the request' and enumerates the review dimensions (correctness, spec-match, test-gap, blast-radius, safe_to_apply). It also disambiguates behavior by stating 'Does not apply the patch.' It stops short of a 5 because it does not explicitly contrast itself with similarly named siblings like jev_evaluate or jev_verify.

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?

It gives an explicit trigger: 'Call before declaring a fix done,' which tells the agent when in a workflow this tool belongs. It does not, however, state when not to use it or name any alternatives, so exclusionary guidance is missing.

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