Inspect the current screen to read visible controls and text, returning observations and element IDs needed for direct actions. Use this to determine the next precise step in task execution.
Read visible controls and text. Use returned observation and element IDs for direct actions. Running task observations are available from computer_status.
| Name | Required | Description | Default |
|---|---|---|---|
| ocr | No | ||
| sessionId | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given annotations already declare readOnlyHint=true and destructiveHint=false, the description adds useful behavioral context: it explains that the tool returns an observation with element IDs intended as input for action tools. It also clarifies that ongoing task observations live elsewhere. No contradictions with annotations.
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?
Three short sentences, each earning its place: the first defines the action, the second explains the output's purpose, and the third routes to a sibling. No filler or redundancy, and the core information is front-loaded.
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?
The tool has no output schema and no parameter descriptions, so the description is the only source of guidance. It covers the general purpose but leaves out crucial invocation details (how to specify ocr, what sessionId identifies) and how it differs from computer_screenshot. An agent would likely need additional context to call it correctly.
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 0%, and the description completely ignores both parameters: it does not explain what sessionId refers to or what the ocr enum values (auto, always, off) do. An agent invoking the tool is left without any hint as to how to construct the object correctly.
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 states a specific verb and resource: 'Read visible controls and text.' It distinguishes itself from siblings by explicitly connecting to 'element IDs for direct actions' and by referencing computer_status for running task observations, which makes the scope clear.
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 description provides concrete usage context: use the returned observation and element IDs to drive direct actions photos. It also directs the agent to computer_status for task observations, naming a specific alternative. It stops short of detailing when not to use this tool versus screenshot or other inspection tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.