Capture a web page or one element by ref as an image for visual inspection of layout, images, or canvas when text reading is not enough.
Screenshot the page (or one element by ref) and return the image. Costs many tokens: prefer browser_read unless you need to see layout, images or a canvas.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | ||
| fullPage | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full load: it discloses the high token cost, that the return value is an image, and the two scoping modes (whole page vs. single element). It does not mention image format, viewport assumptions, or that the operation is non-mutating, but the token-cost warning is genuine behavioral context most tools omit.
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 tight sentences: the capability first, then the cost/alternative rule. Zero filler and the most decision-relevant 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?
No output schema and no annotations, yet the description tells the agent what comes back (an image) and why that is expensive. Missing only minor details like image format and the semantics of fullPage, which is thin for a 2-param tool but not blocking.
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%, so the description must compensate for both parameters. It clarifies 'ref' as targeting one element, but says nothing about 'fullPage' (capture beyond the viewport?), leaving half the parameters undocumented in both schema and prose.
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 ('Screenshot the page'), plus the element-scoped variant via ref, and names the sibling it is not (browser_read). An agent can distinguish it from browser_read and browser_act without opening any schema.
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?
Gives an explicit routing rule: prefer browser_read, and only use this when layout, images or a canvas must be seen. The cost tradeoff that drives the choice is stated, not implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.