Capture a page's accessibility tree as a text snapshot, listing elements with unique IDs for UI automation. Use the newest snapshot instead of a screenshot.
Take a text snapshot of the page based on the a11y tree. Lists elements with a unique uid. Always use the latest snapshot. Prefer this over a screenshot.
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | No | Targets a specific page by ID. Defaults to the selected page. | |
| verbose | No | ||
| filePath | No |
Changes observed during successful MCP inspections.
v0.4.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does add useful behavior: the return is a text tree of elements carrying unique uids, and snapshots go stale ('Always use the latest snapshot'). It omits how the uid is consumed downstream, cost/size characteristics, and whether this is a pure read with no side effects.
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?
Three short sentences, front-loaded with the core action and mechanism, then return shape, then the sibling preference. No filler.
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 3-param read tool with no annotations and no output schema, the description covers purpose and return shape adequately, but leaves two parameters undocumented and gives no detail on output structure beyond 'lists elements with a unique uid'.
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 only 33% – pageId is documented but 'verbose' and 'filePath' have no description in either the schema or the tool description. The description adds zero parameter meaning, so it fails to 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+resource ('Take a text snapshot of the page') and names the underlying mechanism (a11y tree). It also distinguishes itself from the obvious sibling by stating 'Prefer this over a screenshot,' so an agent can choose between take_snapshot and take_screenshot without opening either 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?
Explicitly routes the agent away from the alternative ('Prefer this over a screenshot') and gives a usage constraint ('Always use the latest snapshot'). It stops short of a full when/when-not matrix (e.g., no guidance on when a screenshot is actually preferable), so 4 rather than 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.