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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, destructiveHint), so the description is not the primary burden. But it adds nothing behavioral: it doesn't say whether the click waits for navigation, that it may change page state, or what happens if the ref is stale. Notably, readOnlyHint/idempotentHint are questionable for a click action, yet the description offers no clarifying context.

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 tight sentences with no waste, front-loading the core action before explaining the ref parameter. Every clause earns its place.

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 browser interaction tool with no output schema and one fully undocumented required parameter, the description is incomplete. It handles ref sourcing well but omits post-click behavior (navigation/waiting), error handling for stale refs, and any explanation of page_id.

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 33%, and the description strongly compensates for `ref` by documenting both accepted formats (aria-ref token vs CSS selector), its origin in browser.snapshot, and the preferred form. However, the required `page_id` parameter is undocumented in both schema and description, leaving a real 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 ("Click an element") that is clearly distinct from sibling verbs like browser_hover, browser_fill, and browser_type. However, it never explicitly differentiates from those siblings, so it lands just below the 5 bar.

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?

There is no guidance on when to use click versus alternatives (hover, type, fill, press_key) and no stated prerequisites. The only usage hint is "Prefer the aria-ref token," which is about parameter format choice, not tool selection.

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