CRAP Score MCP

Overview Schema Source Related Servers Discussions Admin

review_changes

Review a coding session's changes against its starting snapshot or revision to get session health and raw CRAP score deltas, so you can confirm which functions improved or regressed before wrapping up.

Instructions

Review a session against its starting snapshot or revision. Use format=chat at completion and show the returned session health and raw CRAP changes in your reply.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "review_changes"
  }
}

Input Schema

Name	Required	Description	Default
`base`	No
`limit`	No
`format`	No		data
`offset`	No
`project`	No
`snapshot`	No
`findingId`	No
`scorecard`	No	With chat format, include a PNG image and its absolute file path.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

B3.1/5.0

Behavior3/5

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

With no annotations supplied, the description carries the full burden. It usefully discloses what comes back (session health and raw CRAP changes) and that chat format should be used at completion, but says nothing about whether the operation mutates state, permission requirements, or how base and snapshot interact.

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

Conciseness4/5

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

Two short sentences with no filler, and the core action is front-loaded before the format directive. Slightly cryptic phrasing ('raw CRAP changes') costs a bit of clarity but nothing is wasted.

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

Completeness2/5

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

An eight-parameter tool with no annotations, no output schema, and near-zero schema descriptions needs far more from the description. Six parameters are effectively undocumented, so an agent cannot confidently supply base, snapshot, or pagination values.

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

Parameters2/5

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

Schema description coverage is only 13% (just scorecard), and the description explains only format=chat. Base, snapshot, project, findingId, limit, and offset get no meaning beyond their names, and the crucial base-vs-snapshot choice is left unresolved.

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 states a specific verb and resource: review a session against its starting snapshot or revision. That distinguishes it reasonably well from siblings like analyze_function_health and scan_repository_hotspots. The term 'session' is never defined, so the resource is slightly ambiguous.

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

Usage Guidelines3/5

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

The only usage directive is 'Use format=chat at completion', which gives a conditional for one parameter but not when this tool should be chosen over analyze_function_health, scan_repository_hotspots, or get_repository_report. No prerequisites or exclusions are stated.

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

Deploy Server