Scans a git diff for skipped tests, suppression comments, unsafe casts and weakened lint or CI config, returning structured findings to catch checks silently disabled in a change.
Engine 3: skipped tests, suppression comments, unsafe casts and weakened lint/CI config added in the diff.
| 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's added value is the diff-scoping behavior (it analyzes changes against a base ref rather than the whole repo) and the specific defect classes flagged, but it says nothing about output shape, severity levels, or whether it blocks/fails. That is useful but thin additional context.
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?
One compact sentence with no filler in the detection list, which is good. However it is a noun-phrase fragment rather than a front-loaded statement of purpose, and the leading 'Engine 3:' token consumes prime space with information an agent cannot act on.
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?
With only two well-documented parameters and no output schema, the definition should carry more weight: what a finding looks like, whether results are per-file or aggregated, and how it relates to the eight sibling checks. The description provides a detection list but no return-value or routing context, leaving an agent unable to predict the response or choose it over prufgate_test_audit.
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%, with base_ref and workspace_path both documented in the schema, so the baseline is 3. The description reinforces that this is a differential scan against a base ref but adds no format details, defaults, or edge-case behavior 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?
The description names a concrete set of things it looks for (skipped tests, suppression comments, unsafe casts, weakened lint/CI config) scoped to the diff, which is more specific than the name alone. But it never states a verb or that this is a scan/detection tool, and the 'Engine 3:' prefix is opaque internal jargon. An agent can guess it flags diff-introduced quality regressions but not with confidence against siblings like prufgate_test_audit or prufgate_full_scan.
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?
There is no statement of when to use this versus prufgate_test_audit (overlapping skipped-test detection) or prufgate_fast_scan/prufgate_full_scan (whole-repo vs diff scope). The 'added in the diff' phrasing implies diff-scoped usage, but no prerequisites, exclusions, or alternative routing are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.