browser_click

Does 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 does not mention what happens after a click—like navigation, state changes, or waiting—nor any side effects like triggering popups or form submissions. It lacks details on error conditions (e.g., if ref is stale or element is hidden) and does not indicate whether the tool is destructive or read-only. The description adds minimal behavioral context beyond the basic action.

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 9 words, efficiently stating the core action. It is front-loaded with the verb 'Click' and immediately clarifies the mechanism ('by its ref from the snapshot'). No redundant information is present. It earns points for brevity, but could be slightly more structured with optional usage notes.

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?

Given the tool has 2 parameters, no output schema, and no annotations, the description is insufficiently complete. It does not explain the return value (e.g., nothing, a success status, or updated page content), nor does it clarify the relationship to sibling tools like browser_snapshot (which generates the ref). The context signals indicate low complexity, but the lack of behavioral and usage guidance leaves gaps for an AI agent.

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 schema description coverage is 100%, so the schema already documents both parameters. The description does not add new meaning beyond the schema; it merely states the tool's main action. The 'element' parameter's human-readable description is covered by the schema, and the description does not elaborate on how the 'ref' is obtained or validated. Baseline 3 is appropriate since the schema does the heavy lifting.

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 'Click an element by its ref from the snapshot' clearly specifies the verb 'Click' and the resource 'element by its ref from the snapshot'. It distinguishes itself from sibling tools like browser_hover, browser_type, and browser_fill by focusing specifically on clicking, and hints at dependency on browser_snapshot for obtaining the ref. However, it could be slightly more explicit about how it differs from browser_select_option or browser_navigate.

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, such as when to use browser_hover or browser_fill. It does not mention prerequisites like the need for a recent snapshot, nor does it exclude inappropriate contexts (e.g., clicking elements that are not interactable). The usage context is only vaguely implied by the relation to snapshots.

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