Skip to main content
Glama
Sign In

Proxylang website translation

by dev.proxylang
OverviewDiscussionsAdmin

Match the language menu to the site

proxylang_style
Idempotent

Restyle the language menu so it looks like part of the site. Read the site's brand color, background, text color, button roundness and dark mode first, then send only the fields to change in style. Colors: #hex, rgb(), hsl() or a CSS color name; each has a Light and a Dark version. Full field list: https://proxylang.dev/agents.md step 7.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent_token": "<agent_token>",
      "style": "<style>"
    },
    "name": "proxylang_style"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleYesFields to change, e.g. {"accent": "#0a7cff", "triggerBgLight": "#ffffff", "triggerTextLight": "#111827", "borderRadius": "pill"}. Fields: triggerBg/triggerText/triggerHover/dropdownBg/dropdownText/bg/text/border + Light|Dark, accent, accentText, borderRadius (rounded|pill|square), size (small|medium|large), dropdownSize, shadowStrength (none|light|medium|strong), glassmorphism, position, displayFormat (code|native|both), flagStyle (none|rectangle|square|circle), animation, darkModeMethod (auto|class), darkModeClass, displayMode (floating|inline: inline needs <div id="proxylang-widget"></div> in the site's nav bar), mobileBreakpoint, draggable, flagFillsTrigger.
agent_tokenYesThe agent_token from proxylang_start.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / style / description
      Previous value: -"Fields to change, e.g. {\"accent\": \"#0a7cff\", \"triggerBgLight\": \"#ffffff\", \"triggerTextLight\": \"#111827\", \"borderRadius\": \"pill\"}. Fields: triggerBg/triggerText/triggerHover/dropdownBg/dropdownText/bg/text/border + Light|Dark, accent, accentText, borderRadius (rounded|pill|square), size (small|medium|large), dropdownSize, shadowStrength (none|light|medium|strong), glassmorphism, position, displayFormat (code|native|both), flagStyle (none|rectangle|square|circle), animation, darkModeMethod (auto|class), darkModeClass."New value: +"Fields to change, e.g. {\"accent\": \"#0a7cff\", \"triggerBgLight\": \"#ffffff\", \"triggerTextLight\": \"#111827\", \"borderRadius\": \"pill\"}. Fields: triggerBg/triggerText/triggerHover/dropdownBg/dropdownText/bg/text/border + Light|Dark, accent, accentText, borderRadius (rounded|pill|square), size (small|medium|large), dropdownSize, shadowStrength (none|light|medium|strong), glassmorphism, position, displayFormat (code|native|both), flagStyle (none|rectangle|square|circle), animation, darkModeMethod (auto|class), darkModeClass, displayMode (floating|inline: inline needs <div id=\"proxylang-widget\"></div> in the site's nav bar), mobileBreakpoint, draggable, flagFillsTrigger."
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, idempotent, non-destructive, open-world operation, so the bar is lower. The description still adds substantive context: it is a partial update ("send only the fields to change"), which aligns with idempotentHint and clarifies that unspecified fields are preserved rather than reset. It does not say whether the restyle takes effect immediately on the live site or is staged, which is the main remaining behavioral gap.

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?

Three sentences, front-loaded with the purpose, then the workflow, then formats and the doc link. Every sentence carries information, though the final documentation URL outsources part of the specification rather than stating it inline.

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

Completeness4/5

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

For a mutation tool with a large nested style object and no output schema, the description covers purpose, partial-update semantics, color formats, and a pointer to the exhaustive field list. What is missing is modest: which tool supplies the site's current brand values, and whether changes apply live or require a publish step.

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

Parameters4/5

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

Schema coverage is 100% and the style property already enumerates the field names, so the baseline is 3. The description adds meaning the schema does not: accepted color syntaxes (#hex, rgb(), hsl(), CSS color names) and the rule that each color has a Light and a Dark variant, plus a pointer to the full field reference. It does not elaborate on non-color params such as position, animation, or mobileBreakpoint beyond what the schema says.

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?

"Restyle the language menu so it looks like part of the site" gives a specific verb (restyle) and resource (language menu), which is clearly distinct from the sibling tools whose names suggest site-wide change, status, and setup. It stops short of explicitly naming the sibling it is not (e.g. proxylang_change_site), so differentiation relies on the reader's inference.

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 description prescribes a workflow order: read the site's brand color, background, text color, button roundness and dark mode first, then send only the fields to change. That is real usage context, but it never names which tool performs that read (proxylang_status or proxylang_check), leaving the agent to guess the prerequisite call.

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

All Proxylang website translation toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources