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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context not in the annotations: output is YAML, refs are embedded inline, and output is truncated at 32KB. It does not say what happens after truncation or whether refs go stale after navigation.

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 the return value, then the ref contract, then the caveat. Four short sentences, all relevant. The explicit 'Do NOT pass the role name' warning slightly overlaps the preceding sentence but is defensible given how commonly that mistake is made.

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?

With no output schema, the description correctly carries the burden of describing the return value (YAML aria tree, eN ref tags, 32KB truncation) and its intended consumer. Remaining gaps — page_id semantics, ref lifetime across navigations, truncation recovery — are minor for a read-only snapshot 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 50% — `in_workspace` is documented in the schema while `page_id` (required) is not. The description adds no meaning for either input parameter; its discussion of `ref` concerns sibling tools' arguments, not this tool's schema. With the coverage gap uncompensated, this sits below the baseline 3.

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 ('Return a YAML aria_snapshot of the page DOM') and defines the distinguishing output artifact, the `[ref=eN]` tokens. An agent can tell this apart from browser_evaluate or browser_console_messages 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?

Clearly explains the downstream workflow — the eN token is the value to pass to browser.click/fill/type/press_key — and warns against the common misuse of passing a role name. It gives no explicit 'when not to use this' or alternative (e.g. browser_evaluate for non-interactive inspection), so it stops short of a full 5.

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