Skip to main content
Glama

xml_load

Compile Panorama XML (and optional CSS) with CSDK and load it into the live UI (~2s).

Instructions

Compile Panorama XML (and optional CSS) with CSDK and load it into the live UI (~2s).

mode='append': create a child panel (id replaces any existing child with that id) under target. mode='replace': load the layout into target itself, replacing its contents. Refused for the UI root, the bridge panel (and its ancestors), and any panel whose type isn't plain Panel (loading into a C++ panel crashes the game). xml: a full ... layout or a bare fragment (wrapped automatically). Referenced scripts/styles must exist in the game or the addon. css: real Panorama CSS (pseudo-classes, animations, @define all work) compiled as this layout's stylesheet, included after the layout's own so it wins ties.

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": {
      "xml": "<xml>"
    },
    "name": "xml_load"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
uiNoauto
cssNo
xmlYes
modeNoappend
targetNoroot

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations at all, the description takes on the full disclosure burden and largely meets it: it states the runtime cost, that replace destroys the target's contents, that certain targets are refused, and that loading into a C++ panel crashes the game. It also explains CSS precedence relative to the layout's own <styles>, which is exactly the kind of behavior an agent could not get elsewhere.

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?

Front-loaded with the one-line purpose, then broken out by parameter with bolded mode labels, so scanning is easy. It is dense but nearly every clause carries information; the only slight drag is the compressed parenthetical about bridge panel ancestors.

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?

An output schema exists, so return values need not be explained, and the description covers the destructive semantics, failure conditions, and asset/script preconditions that matter for a load tool. The only omission is the 'ui' parameter, which is minor against the rest of the coverage.

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 0%, so the description must carry parameter meaning and it does for five of six: xml (full root or auto-wrapped fragment), css (real CSS, pseudo-classes, animations, @define, ordering), mode (append vs replace), target (root default, refusal cases), and id (replaces an existing child with the same id). The 'ui' parameter is never mentioned, leaving one undocumented field.

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

Purpose5/5

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

The description opens with a specific verb and resource: compile Panorama XML/CSS with CSDK and load it into the live UI, including an approximate cost (~2s). That is enough to separate it from siblings like css_apply, compile_source, or layout_live_edit without opening a schema.

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 two modes are clearly described, including how append vs replace behave and the hard exclusions for replace (UI root, bridge panel and ancestors, non-plain-Panel types). It stops short of explicitly contrasting this with sibling tools such as css_apply or compile_source when both seem plausible, so an agent must still infer that boundary.

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