mcp-mt5

Overview Schema Source Related Servers Discussions Admin

regression_check

Read-onlyIdempotent

Compares a baseline report to a candidate report using optional percent thresholds to detect metric regressions. Deprecated: use compare_reports.

Instructions

DEPRECATED (removed in 0.6.0): use compare_reports(baseline, candidate, guards=...).

Input Schema

TableJSON Schema

Name	Required	Description
`guards`	No	Percent thresholds per summary key.
`baseline`	Yes	Absolute path to the baseline report.
`candidate`	Yes	Absolute path to the candidate report.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.5.0Sep 11, 2026

addedInput schema / properties / baseline / description

Added value: +"Absolute path to the baseline report."

addedInput schema / properties / candidate / description

Added value: +"Absolute path to the candidate report."

addedInput schema / properties / guards / description

Added value: +"Percent thresholds per summary key."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "regression_checkDictOutput",
+  "type": "object"
+}

First observedv0.4.1Jun 11, 2026

TDQS

A4.5/5.0

Behavior5/5

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

It states the tool is deprecated and removed, a critical behavioral fact not captured by the annotations (readOnlyHint, idempotentHint). This goes beyond structured metadata and tells the agent the tool is non-operational, preventing any attempt to invoke it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The entire description is a single, front-loaded sentence with 'DEPRECATED' at the very start, immediately signaling the key message. Every word is essential, and the instruction to use the replacement is clear and succinct.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a deprecated tool, this is complete. It tells the agent whether to use it (no) and exactly what to use instead, including the call signature. No additional information about return values or behavior is needed because the tool is non-functional.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 100% of parameter descriptions, so the baseline for this dimension is 3. The description adds no further semantics about the tool's own parameters; it only references parameters in the alternative tool. This is acceptable for a deprecated tool, but no extra value is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool is DEPRECATED and removed in 0.6.0, which tells an agent it should not be used. It also points to the specific replacement tool, compare_reports, distinguishing it from siblings. While it does not explain the original function, that is unnecessary given the deprecation status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description directly instructs the agent to use compare_reports(baseline, candidate, guards=...), providing the exact alternative and required parameters. This is an explicit, unambiguous usage directive with no room for misinterpretation.

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