Skip to main content
Glama
RapidMiner / Altair AI Studio MCP

RapidMiner / Altair AI Studio MCP

rm_screenshot

Capture the active AI Studio window or a specific UI component as a PNG/JPG image to inspect layout and controls, including on Wayland.

Instructions

Screenshot an AI Studio window (default: active) or a single component. Rendered from inside the app, so it works on Wayland. Coordinates in the image = window coordinates when scale=1.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "rm_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoComponent id from rm_ui_tree / rm_ui_find
nameNoMatch Swing component name
textNoMatch visible text / label (substring, case-insensitive)
classNoMatch Java class name, e.g. JButton, JTree
exactNoExact (not substring) text match
indexNoWhich match to use when several match (0-based)
scaleNoImage scale; pass the same scale to rm_click/rm_drag when using x/y
formatNojpg
windowNoWindow id from rm_windows (default: active window)
tooltipNoMatch tooltip text

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does add real behavioral context the agent could not otherwise know: rendering happens inside the app, so it works on Wayland where external capture fails, and the coordinate mapping rule ties image pixels to window coordinates at scale=1. It omits how the image is delivered back (inline data, file path) and any size or performance limits, which are meaningful for a screenshot tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with no filler. Scope and default come first, then the non-obvious environmental and coordinate facts, which is the right order for an agent scanning the definition.

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

Completeness3/5

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

For a 10-parameter screenshot tool with no annotations and no output schema, the essentials are covered but the return channel is not: the description never says whether the image is returned inline, saved to a path, or otherwise handed back. It also leaves unstated the mutual exclusivity of the many component selectors (id, name, text, class, tooltip). Adequate but short of complete.

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 already 90%, so the baseline is 3, and the description adds a genuinely new rule beyond the schema: image coordinates equal window coordinates when scale=1, which is the key to feeding x/y into the click and drag tools. The 'default: active' note on the window selector reinforces what the schema already states, so the gain is one solid addition rather than comprehensive parameter guidance.

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?

States a concrete verb and resource: 'Screenshot an AI Studio window (default: active) or a single component.' The two targeting modes are explicit, so an agent knows it can capture either the whole window or one component. No sibling is named, but no sibling appears to be a competing screenshot tool.

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?

Implicitly says when to use the window mode by giving the 'default: active' behavior, and 'or a single component' signals the component-selection path. It never states prerequisites, when to avoid it, or how it relates to inspection tools like the tree finder referenced in the schema. Usage is inferable rather than stated.

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