Capture a PNG image of the current browser tab, or the full scrollable page, to return visual context for vision-capable AI models.
Take a PNG screenshot of the current tab. Returns an image (for vision-capable models).
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | No | ||
| fullPage | No | Capture the full scrollable page (default false) |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the output is an image (PNG) and that vision capability is needed, which annotations would not have covered. It does not disclose default capture scope (viewport vs full page), where the image is returned (inline data vs path), or any permission/size constraints.
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, front-loaded with the action and then the return type. Nothing superfluous.
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?
No output schema and no annotations, so the description does the heavy lifting on the return value, which it handles. But for a 2-parameter tool with one undocumented parameter and ambiguous overlap with 'snapshot', the definition is only minimally complete.
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 50% – 'fullPage' is documented in the schema, but 'tabId' is undocumented in both schema and description. The description mentions no parameters at all, so it does not compensate for the coverage gap.
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?
States a specific verb and resource ('Take a PNG screenshot of the current tab'), so the agent knows exactly the action. However, it offers no differentiation from the sibling 'snapshot', which is exactly the tool an agent might confuse it with.
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 guidance on when to prefer this over 'snapshot', 'get_html', or 'evaluate'. The 'for vision-capable models' clause implies a condition, but it is about model capability, not usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.