Capture the RAW camera frame — no perspective warp, no crop to the calibrated
screen quad. Use this to see exactly what the camera sees before any correction,
e.g. when troubleshooting why take_screenshot looks wrong, or before adjusting
corners with get_corners/set_corners.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description explains the core behavior (no warp/crop) but omits potential side effects or requirements. Adequate for a simple capture tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no waste, front-loaded with the key purpose. Efficiently communicates all essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters, no output schema, and a straightforward action, the description provides complete context for usage and purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Zero parameters, so baseline 4. The description adds no parameter info but the schema fully covers the empty parameter set.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Capture the RAW camera frame' and contrasts with corrections, making the purpose unmistakable and distinct from sibling tools like take_screenshot.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides concrete use cases: 'when troubleshooting why take_screenshot looks wrong, or before adjusting corners with get_corners/set_corners', directly guiding when to choose this tool over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct action: clicks, screenshots (raw, corrected, calibration aids), keyboard input, mouse movement, scrolling, and corner calibration. There is no ambiguity between tools.
Tool names mix conventions: some are single verbs (click, scroll, key), some are verb_noun (move_mouse, set_corners, type_text), and some are longer phrases (take_screenshot_with_crosshair). Although readable, the inconsistency is notable.
With 12 tools, the server covers all essential interactions for camera-based screen control without being bloated or sparse. Each tool has a clear role.
The tool set covers clicking, typing, key combinations, mouse movement, scrolling, and multiple screenshot modes including calibration aids. Missing drag/swipe functionality is a minor gap.