Skip to main content
Glama
faze79

WpfVisualTreeMcp

by faze79
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

wpf_scroll

Sends a real mouse wheel event to a WPF element to scroll or trigger app-defined input, targeting by element handle or AutomationId. Use it to test how a running app responds to wheel input.

Instructions

Send a real mouse wheel event over a visible element. delta is signed wheel units: 120 = one notch, positive scrolls up (or right with horizontal=true), negative down/left; nonzero range -12000..12000. Optional paired x/y are local WPF DIPs, default center. Moves the mouse and activates the app. Supports native hosted canvases. The app decides whether to scroll, zoom or ignore input; verify the result. STATE-CHANGING. Target by exactly one of element_handle or automation_id (exact, case-sensitive AutomationProperties.AutomationId). Use root_handle with automation_id to scope lookup; missing or duplicate IDs fail before input.

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
deltaYes
horizontalNo
root_handleNo
automation_idNo
element_handleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.17.2
    • addedInput schema / properties / automation_id
      Added value: +{
+  "default": null,
+  "type": "string"
+}
    • addedInput schema / properties / element_handle / default
      Added value: +null
    • addedInput schema / properties / root_handle
      Added value: +{
+  "default": null,
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "element_handle",
-  "delta"
-]New value: +[
+  "delta"
+]
  2. Addedv0.17.1

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden, and it does well: it openly flags "STATE-CHANGING," warns that the mouse is moved and the app activated, and discloses pre-input failure conditions (missing or duplicate IDs fail before input) plus support for native hosted canvases. It doesn't say whether the scroll is reversible or what the response looks like, 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?

Purpose is front-loaded in the first clause, followed by parameter semantics, then behavioral warnings, then targeting rules. Every sentence carries information, though the dense, semicolon-heavy packing makes it harder to scan.

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?

For a 7-parameter, no-annotation, no-output-schema tool, the definition covers targeting resolution, parameter meaning, side effects, and expected verification steps. Nothing an agent needs to invoke it correctly 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 coverage is 0%, so the description must compensate, and it does for the critical parameters: delta units/sign/range (-12000..12000, 120 per notch), x/y as local WPF DIPs defaulting to center, horizontal axis flipping, and the mutually exclusive element_handle/automation_id targeting with root_handle scoping. Only root_handle's standalone behavior is left somewhat implicit.

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?

Names a specific verb and resource: "Send a real mouse wheel event over a visible element." It implicitly distinguishes itself from siblings like wpf_click_element and wpf_move_mouse by emphasizing the wheel event and noting that mouse movement is only a side effect, not the purpose.

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?

Gives concrete when-to-use mechanics (targeting by element_handle or automation_id, scoping via root_handle) and tells the agent to verify results because "The app decides whether to scroll, zoom or ignore input." It never names an alternative sibling tool or states when NOT to use this one, so it stops short of a 5.

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