Run a deterministic review of the diff against a base git ref to detect fabricated fallbacks, weakened tests, disabled checks, and missing authorization scoping.
Engine 6: deterministic review of the diff against base_ref (default: resolved like prufgate check --changed).
| Name | Required | Description | Default |
|---|---|---|---|
| base_ref | No | Base git ref to diff against, e.g. origin/main | |
| workspace_path | No | Path to the repository to scan | . |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: the review is deterministic and base_ref is resolved the way 'prufgate check --changed' resolves it. It never says what the review produces (findings list, severities, exit status), which matters since there is 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?
A single tight sentence with no padding, and the core object (diff against base_ref) is front-loaded. The only wasted token is the meaningless 'Engine 6:' prefix, which also front-loads jargon instead of intent.
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 review/analysis tool with no output schema, the description leaves the agent unable to predict the result: no mention of what a 'review' returns, whether it blocks, what categories of issues it checks, or how it relates to the sibling check tools. Two optional params keep the surface small, but the missing return semantics is a real gap.
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 both parameters are already documented in the schema; baseline is 3. The description adds only a little beyond that: the defaulting/derivation behavior for base_ref. workspace_path is not discussed at all.
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?
Names a verb ('deterministic review') and a resource ('the diff against base_ref'), so the rough shape is clear. But 'Engine 6' is opaque internal jargon and 'review' is never defined (lint? findings? pass/fail?), and the description does not differentiate it from the sibling prufgate_diff_guard, which sounds like it covers the same ground.
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 only usage signal is the parenthetical 'default: resolved like prufgate check --changed', which implies a CI-style changed-files workflow but is stated as a default-resolution detail rather than a when-to-use rule. There is no statement of when to pick this over prufgate_diff_guard, prufgate_fast_scan, or prufgate_full_scan.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.