Skip to main content
Glama
bitbank-lab-mcp

bitbank-lab-mcp

Official
by bitbankinc

get_ui_snapshot

Return the recent preview tool response snapshot for a confirmation UI iframe so embedded widgets can restore their state when host tool-result notifications aren't delivered.

Instructions

[Internal / MCP Apps] 確認 UI(iframe)向けに、直近の preview 系ツール応答のスナップショットを返す。 ホストがツール結果通知(ui/notifications/tool-result)を配信しない場合の UI 自己復元用。 LLM が会話の応答生成のために呼ぶ必要はない(preview 系ツールの応答に同じ内容が含まれる)。

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": {
      "resource_uri": "<resource_uri>"
    },
    "name": "get_ui_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
resource_uriYesスナップショットを取得する MCP Apps リソース URI(ウィジェット自身の URI を指定する)
confirmation_tokenNo[Internal] 確認 UI が受け取り済みであることをサーバーに伝えるための値。LLM は指定しない

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.0
    • addedInput schema / properties / confirmation_token
      Added value: +{
      +  "description": "[Internal] 確認 UI が受け取り済みであることをサーバーに伝えるための値。LLM は指定しない",
      +  "type": "string"
      +}
  2. Addedv0.4.1

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses that this is an internal UI-support tool, that it reads the latest preview response rather than producing new data, and that its content duplicates what preview tools already return. It does not discuss error behavior when no prior preview response exists, which keeps it from a 5.

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 short sentences, front-loaded with the [Internal / MCP Apps] marker and the core action, then the rationale, then the caller guidance. Slightly repetitive in restating that the content is duplicated, but nothing is wasted.

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 two-parameter, no-output-schema internal tool, the description covers purpose, audience, and the reason it exists. The only gap is what happens when no prior preview response is available, which is minor given the schema fully documents inputs.

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

Parameters3/5

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

Schema description coverage is 100% and both parameters are documented in the schema, including the enum of resource URIs and the note that the LLM should not supply confirmation_token. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 ('returns a snapshot of the most recent preview-type tool response') and scopes it to the confirmation UI (iframe). The [Internal / MCP Apps] tag and the note that the same content appears in preview tool responses make it clearly distinguishable from the analysis/render siblings.

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

Usage Guidelines5/5

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

Explicitly gives both sides: it exists for UI self-restoration when the host does not deliver ui/notifications/tool-result, and the LLM should not call it for generating conversation responses. That is a direct when-to-use / when-not-to-use statement.

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