Skip to main content
Glama
fgui-agent-bridge

fgui-agent-bridge

by Wilson520403

fgui_clear_atlas_markers

Removes incorrect atlas="alone" markers from a FairyGUI package.xml on disk, previewing by default and only clearing markers that fit actual constraints.

Instructions

清除磁盘 package.xml 中错误的 atlas="alone" 标记(只处理按真实约束装得下的图片)。

默认只预览,execute=True 才写;可用 item_ids / item_names 限定目标。 这是带外修改:绕过编辑器对象模型,不可撤销、不进 Agent 撤销栈。执行前会保存 当前包并备份 package.xml,写后回读磁盘并 Dispose + 重开包。包内有未保存文档时 直接拒绝;有已保存的打开文档时,需要显式 close_open_documents=True 才会关闭它们。

只清除错误标记,不写任意图集归属;装不下或无法判定的 alone 标记会保留并在 held 里说明原因。

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": {
      "package_name": "<package_name>"
    },
    "name": "fgui_clear_atlas_markers"
  }
}

Input Schema

NameRequiredDescriptionDefault
executeNo
item_idsNo
item_namesNo
package_nameYes
close_open_documentsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.25

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so thoroughly: it declares the operation out-of-band (bypasses the editor object model), irreversible, and excluded from the Agent undo stack. It further discloses the save-then-backup-package.xml sequence, the post-write re-read plus Dispose/reopen cycle, and the refusal conditions for unsaved versus saved-open documents.

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?

The core action and its preview-by-default behavior are front-loaded, followed by risk disclosure and then the conservative-hold guarantee. It is fairly dense across several paragraphs, but each sentence adds distinct operational information; only the wording around the reopen cycle could be tightened.

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?

Given a five-parameter mutating tool with no annotations and an output schema, the description covers safety profile, preconditions, side effects, and the meaning of the held output field for retained markers. Nothing an agent needs to decide whether and how to invoke it is missing.

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 description coverage is 0%, so the description must compensate, and it covers the key semantics: execute as the preview/write switch, item_ids and item_names as target limiters, and close_open_documents as a required opt-in before saved open documents are closed. package_name is only implicitly covered as the target package, leaving a small gap.

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?

States a specific verb and resource: clearing erroneous atlas="alone" markers from the on-disk package.xml, scoped to images that actually fit under real constraints. No sibling tool performs this operation, and the description also draws the boundary against writing arbitrary atlas assignments, so the agent can identify it unambiguously.

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?

Explicitly states the default is preview-only and that execute=True is required to write, and explains how to narrow targets via item_ids/item_names. It also gives the preconditions that cause refusal (unsaved documents) and the escape hatch (close_open_documents=True). It does not explicitly route the agent from the closely related fgui_analyze_atlas_fit, which is the one clear missing usage link.

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

Deploy Server

Other Tools