Skip to main content
Glama

dittu

by io.github.BorisGujvin

take_screenshot_with_crosshair

Capture the screen, crop tightly around (nx, ny), zoom in, and draw a crosshair
at exactly that expected position.

Use this for screen-corner calibration: move_mouse(nx, ny) near a screen edge,
then call this to see whether the actual cursor lines up with the crosshair
(where it SHOULD be if calibration is perfect). If the cursor is offset from the
crosshair, or missing entirely (edge is cropped out of frame), corners need
adjusting — see get_corners/set_corners.

nx, ny: the same coordinates you passed to move_mouse.
zoom: magnification factor for the cropped region (default 4x).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nxYes
nyYes
zoomNo

TDQS

A4.9/5.0
Behavior5/5

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

Describes the effects: capture, crop, zoom, draw crosshair, and mentions possible outcomes (cursor offset or missing). Since no annotations exist, the description fully covers behavioral aspects without contradiction.

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 paragraphs with front-loaded purpose: first explains what it does, second explains when to use. Every sentence contributes value; no unnecessary words.

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?

Sufficient for calibration use case with 3 parameters and no output schema. However, it does not explicitly state what the tool returns (e.g., an image), which would be helpful but not critical given the context.

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

Parameters5/5

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

Despite 0% schema description coverage, the description explains nx and ny as 'the same coordinates you passed to move_mouse' and zoom as 'magnification factor (default 4x)'. This adds essential meaning beyond the schema's type/default fields.

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?

The description clearly states the tool captures a screen region, crops around (nx, ny), zooms, and draws a crosshair. This is a specific verb+resource combination that distinguishes it from siblings like take_screenshot and take_screenshot_with_grid.

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 says to use for screen-corner calibration after move_mouse, and provides guidance on interpreting results (cursor offset or missing indicates need for get_corners/set_corners). Clearly separates when to use this vs alternative tools.

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

All dittu toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: click actions, mouse movement, keyboard input, scrolling, screen captures (raw, calibrated, with grid or crosshair), and calibration. No overlap between tools.

Naming Consistency5/5

All tools use snake_case verb_noun pattern consistently (e.g., get_corners, take_screenshot, set_corners), with longer names following the same convention (e.g., take_screenshot_with_crosshair).

Tool Count5/5

12 tools are well-scoped for remote computer control and calibration, covering essential actions without being excessive or insufficient.

Completeness4/5

The set covers core operations (click, type, scroll, screenshot, calibration) but lacks a dedicated drag or right-click tool, which agents may need to work around.

Resources