Capture a screenshot of a specific element on a Safari page using its CSS selector, returning a base64 image for direct use in automation.
Take a screenshot of a specific element (by CSS selector). Returns a base64 image.
| Name | Required | Description | Default |
|---|---|---|---|
| receipt | No | Tab receipt from safari_new_tab — pins this call to that tab (survives reconnects/subagents) | |
| selector | Yes | CSS selector of the element to capture |
Changes observed during successful MCP inspections.
v2.18.1Input schema / properties / receiptAdded value: +{
+ "description": "Tab receipt from safari_new_tab — pins this call to that tab (survives reconnects/subagents)",
+ "type": "string"
+}v2.11.6v2.11.3v2.10.9v2.10.8v2.10.5v2.10.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It does disclose the return format ('Returns a base64 image') and target scope, but it does not mention visibility requirements, scrolling behavior, or what happens if the selector matches nothing.
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 short sentences with no filler. The core action is front-loaded, and the return format is a useful second sentence that earns its place.
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?
For a simple two-parameter tool, the description plus fully documented schema is mostly sufficient: the required selector, optional tab receipt, and base64 return are all covered. Remaining gaps, such as visibility requirements and error behavior, are relatively low-stakes for a screenshot operation.
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 100%, so the baseline is 3. The description adds only 'by CSS selector', which largely restates the selector parameter's role, and provides no additional meaning for the receipt parameter beyond the schema.
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 target: 'Take a screenshot of a specific element (by CSS selector).' This clearly differentiates it from the likely full-page sibling safari_screenshot by narrowing scope to an element, though it does not explicitly name the alternative.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The phrase 'specific element' implies use for element-level captures rather than full-page screenshots, but the agent must infer the boundary with safari_screenshot.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.