Captures a PNG of the current viewport or full page for visual verification when text snapshots are insufficient.
A PNG of the viewport (or the whole page). Prefer browser_snapshot: text is far cheaper than an image.
| Name | Required | Description | Default |
|---|---|---|---|
| full_page | No | The whole page, not only what is in view |
Changes observed during successful MCP inspections.
v0.7.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the context-cost dimension ('an image' is expensive), which is genuinely useful for an agent budgeting tokens, but says nothing about side effects such as whether full_page capture alters scroll position or viewport state.
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 clauses, zero filler, with the output artifact stated first and the cheaper alternative second. The fragment style is terse enough that the primary action is never stated as a sentence, which slightly undercuts front-loading.
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?
One optional parameter at full schema coverage, annotations present, and no output schema — so the description usefully names the return type (PNG). Adequate for this complexity, with only the tool's actual invocation purpose left implicit.
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 full_page is documented as 'The whole page, not only what is in view', which duplicates the description's parenthetical almost verbatim. No additional semantics (defaults, behavior when omitted) are contributed 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 identifies the produced artifact precisely ('A PNG of the viewport (or the whole page)'), and the parenthetical maps directly onto the single parameter. It implicitly distinguishes itself from browser_snapshot by naming it as the text alternative, though the action verb ('capture') is left implied.
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?
Explicitly routes the agent to sibling browser_snapshot with a stated reason ('text is far cheaper than an image'). It gives the negative/preference case but never states the positive case — when a screenshot is actually required (visual layout, rendering bugs, images).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.