Detect visual changes in a specified screen region by polling at set intervals. Get alerted when the area updates, enabling automated workflows to react to on-screen activity.
Monitor a screen region for changes
| Name | Required | Description | Default |
|---|---|---|---|
| x | Yes | ||
| y | Yes | ||
| width | Yes | ||
| height | Yes | ||
| interval_ms | No | Check interval in milliseconds | |
| duration_seconds | No | How long to monitor (max 30 seconds) |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description bears the full burden of disclosing behavior. 'Monitor' implies repeated checking over time, but the description does not state whether the call blocks, polls continuously, stops after duration_seconds, or what it returns when a change is detected.
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?
The description is a single focused sentence with no filler, and the core action is front-loaded. It is appropriately concise, though the brevity contributes to under-specification in other dimensions.
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?
With no output schema, no annotations, and six parameters including timing controls, this one-line description is not complete enough for reliable invocation. An agent is left to guess the return value, coordinate semantics, and what 'changes' means in terms of output or termination.
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?
Schema description coverage is only 33% and the description does not compensate. 'Screen region' loosely maps to x, y, width, and height, but the description omits coordinate origin, units, and any meaning for interval_ms or duration_seconds beyond the schema's own minimal text.
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 uses a clear verb-resource pair ('Monitor a screen region') and the purpose 'for changes', which distinguishes it from sibling one-shot capture tools like capture_region. It doesn't explicitly name a sibling, but the wording is sufficient to convey the core operation.
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?
The phrase 'for changes' implies the tool should be used when change detection is needed rather than a one-off screen capture, but no explicit when-to-use or when-not-to-use guidance is given. Alternatives such as capture_fullscreen or capture_region are not mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.