Skip to main content
Glama
Master CSS MCP

Master CSS MCP

Official

Compare Master CSS Output

mastercss_css_compare
Read-onlyIdempotent

Compare Master CSS class lists, source buffers, or before/after project snapshots to identify changed definitions and known consumers, without verifying browser rendering.

Instructions

Compare class lists or source buffers under one manifest, or pass beforeSnapshot and afterSnapshot to compare resolved projects, including changed definitions and known consumers. Does not verify browser rendering.

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": "mastercss_css_compare"
  }
}

Input Schema

NameRequiredDescriptionDefault
contextNo
filePathNo
afterHtmlNo
beforeHtmlNo
afterContentNo
afterSnapshotNo
beforeContentNo
afterClassListNo
beforeSnapshotNo
beforeClassListNo

Output Schema

NameRequiredDescriptionDefault
resultYes
versionYes
metadataYes
diagnosticsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value by stating what the comparison surfaces ('changed definitions and known consumers') and what it does not do (browser rendering). It is silent, however, on the critical behavioral question raised by zero required parameters: what happens when no mode-selecting input is supplied.

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 tight sentences with no filler, front-loading the primary mode before the snapshot mode and closing with the limitation. The phrase 'under one manifest' is compressed to the point of ambiguity, which slightly undercuts the efficiency.

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

Completeness3/5

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

An output schema exists, so return values need no explanation. But for a 10-parameter tool with nested objects, the description omits the mutual-exclusivity rules between parameter modes and does not say whether inputs may be mixed or which combination is required, leaving the agent to guess at invocation shape.

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 0% across 10 parameters with two deeply nested snapshot objects, so the description carries the full burden. It names beforeSnapshot/afterSnapshot and gestures at the class-list, HTML and content parameter groups, but never disambiguates filePath vs context vs beforeHtml/beforeContent, nor explains the snapshot structure (version consts, manifest, sources, outputs). This is far short of compensating for the coverage gap.

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?

Uses a specific verb (compare) with two named resources: class lists/source buffers under one manifest, and resolved projects via beforeSnapshot/afterSnapshot. An agent can tell what class of operation this is without opening the schema, though it never names or rules out any sibling tool.

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

Usage Guidelines4/5

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

The 'or' construction effectively describes two operating modes and the inputs that select them: pass beforeSnapshot/afterSnapshot to compare whole resolved projects, otherwise compare class lists or source buffers. It also carries one explicit exclusion ('does not verify browser rendering'), but gives no prerequisites or guidance on choosing between the class-list and source-buffer variants.

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