snapshot

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden. It usefully reveals that the default window scope truncates web pages to the viewport and that ocr is a fallback for inaccessible apps, implying differing cost and fidelity, but it never states that this is a read-only operation, that refs are intended as handles for follow-up actions, or what happens when output exceeds max_nodes.

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?

Front-loaded with an example of the return format, then compact named definitions per scope and one line for filter. The telegraphic style ('scope: window=...') is dense but scannable; almost no wasted text, though the compressed punctuation slightly reduces first-read clarity.

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 three-parameter, read-oriented tool with no annotations and no output schema, the description covers the core behavior and two of three parameters well. It remains incomplete on truncation via max_nodes and on the purpose of refs, which is the main reason an agent would call this tool.

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 coverage is 0%, so the description must compensate, and it does: all five scope enum values are given operational meaning and filter is explained as a substring line filter. The gap is max_nodes, which appears in the schema with a default of 250 but is never mentioned, leaving truncation behavior unexplained.

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 states a specific verb and resource: a compact list of visible elements with refs, plus a concrete output example (`e12 button "Install"`) that pins down the format. It does not explicitly distinguish itself from siblings like screenshot or find, so the agent must infer that this returns text elements rather than pixels.

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?

Guidance is embedded in the scope definitions — choose page for off-screen web content, ocr for apps without accessibility, screen for everything visible — which effectively tells the agent when each mode applies. There is no explicit statement of when to prefer snapshot over screenshot or find, and no preconditions or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.