browser_snapshotCapture a structured snapshot of a page's DOM to inspect its current state. Limit tree depth, child nodes, or scope to a specific element for efficient parallel browser automation.
Return a structured page snapshot.
| Name | Required | Description | Default |
|---|---|---|---|
| maxDepth | No | Max tree depth (default 4). | |
| selector | No | Scope to an element; omit for document body. | |
| sessionId | Yes | ||
| maxChildren | No | Max children per node (default 20). |
Changes observed during successful MCP inspections.
v0.1.14Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states only that a snapshot is returned, but gives no details about side effects (likely read-only), scope of the snapshot (e.g., entire page vs. subtree), or output format. The phrase 'structured' is vague and does not clarify what the agent can expect.
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?
The description is a single sentence with no excess words. It is efficiently structured and front-loaded with the core purpose. No word is wasted, though the brevity itself contributes to the under-specification captured in other dimensions.
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 tool with four parameters, no output schema, and no annotations, the description is insufficiently informative. It does not state the return type, pagination or depth behavior, or how it relates to the many sibling browser_* tools. An agent would have to rely on the schema and tool name to understand the full behavior, which is incomplete.
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?
The description adds no parameter-level information; it only describes the overall action. The schema already documents maxDepth, selector, and maxChildren but leaves sessionId unexplained. With 75% schema coverage, the description could compensate for unspecified parameters but does not, leaving sessionId and the relationship between parameters to the schema alone.
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 clearly states a specific action ('Return') and a resource ('structured page snapshot'). It is not a tautology and conveys the tool's core function. However, it lacks differentiation from siblings like browser_get_page_structure, which might also return a page snapshot, so it doesn't fully disambiguate.
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 description provides no guidance on when to use this tool versus alternatives. There is no mention of use cases, conditions, or exclusions, and no references to sibling tools like browser_get_page_structure. An agent must infer its niche from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.