Save the current viewport as a PNG file and return its file path for use in page context. Optionally crop the capture to a specific element with a CSS selector.
현재 화면을 PNG 파일로 저장하고 경로를 돌려준다. 이미지는 대화에 넣지 않는다.
| Name | Required | Description | Default |
|---|---|---|---|
| selector | No | 이 선택자로 찾은 첫 요소 주변만 잘라낸다. 생략 시 뷰포트 |
Changes observed during successful MCP inspections.
v0.3.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and reveals meaningful behavior: output is a saved file path, the image is not attached to the conversation, and the file format is PNG. It does not cover details like file location or overwriting, but the most decision-relevant behaviors are disclosed.
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 first states the core action and return value, the second states a crucial limitation for the agent. Every sentence 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 tool with one optional parameter covered by the schema, the description plus schema is complete: it states what is captured, the file format, the return value, and that the image will not be visible in conversation. No output schema is needed to understand what the tool returns.
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% and the schema already explains the selector parameter clearly (crop around the first matching element, viewport if omitted). The description adds no parameter-level information, so the schema-heavy baseline of 3 is appropriate.
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 specific verb-resource pair: saves the current screen to a PNG file and returns the path. It is clear and unambiguous against the sibling tools, though it does not explicitly name an alternative or contrast with another action.
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 intended use is implied by the name and the action ('current screen'), but there is no explicit guidance on when to prefer screenshot over open/wait/status/done/close or any exclusions. An agent can infer the primary case but is given no context about alternatives or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.