Detect weakened test assertions and fake mocks by comparing original and modified test code, so you can block silent fake success before merging.
Anti-Silent-Fake-Success: Checks if proposed edits weaken test assertions or inject fake mocks.
| Name | Required | Description | Default |
|---|---|---|---|
| modifiedTestCode | Yes | Proposed test file contents | |
| originalTestCode | Yes | Original test file contents |
Changes observed during successful MCP inspections.
v0.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It names the two failure modes it detects, which is real behavioral content, but says nothing about whether the check is read-only, whether it blocks or only reports, or what verdict/response the agent receives — critical for a gate-style tool.
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 front-loaded sentence with no filler, and the distinctive anti-pattern label comes first. It is arguably over-compressed given how little guidance surrounds it, but nothing in it is wasted.
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 no output schema and no annotations, the description must convey the result shape (pass/fail verdict, findings) and the calling context; it conveys neither. For a gate the agent is expected to act on, this leaves the agent unable to interpret or act on the response.
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 coverage is 100%, with both parameters documented as 'test file contents', so the baseline is 3. The description reinforces the comparison semantics ('proposed edits' vs. implicitly original) but adds no format, size, or framing requirements 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?
Specific verb+resource: 'Checks if proposed edits weaken test assertions or inject fake mocks' on a test-integrity target. The framing ('Anti-Silent-Fake-Success') plus the concrete detection criteria distinguish it from siblings like truthgate_inspect_action and truthgate_mask_context. It stops short of a full 5 because it never explicitly says it compares original vs. modified test files, though the schema implies that.
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 'Anti-Silent-Fake-Success' label implies the trigger condition — call this before accepting edits that touch test files — but that is inferred, not stated. There is no explicit when-to-use, when-not-to-use, or comparison to the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.