Clicks a web page element by element_index from a recent browser snapshot, falling back to a CSS selector; refresh the snapshot to avoid stale-element errors.
Click a page element, preferring element_index; selector is a fallback, xy pixel coordinates not recommended. Use element_index from the latest browser_snapshot (valid 30s); returns element_no_longer_valid when stale.
| Name | Required | Description | Default |
|---|---|---|---|
| xy | No | ||
| button | No | ||
| selector | No | ||
| element_index | No |
Changes observed during successful MCP inspections.
v0.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the 30-second staleness window and the specific failure mode ('element_no_longer_valid'). It omits whether the click waits for navigation or how the button parameter affects behavior, so it is strong but not complete for a mutation-style interaction.
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 dense sentences with the preferred path front-loaded before the fallbacks, and the staleness/error caveat last. No filler text at all.
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 4-parameter tool with no annotations and no output schema, this covers the critical decision points and one return/error value. The only real gap is the undocumented 'button' parameter and the absence of any note on what a successful click returns.
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 for three of four parameters: element_index (source and 30s validity), selector (fallback role), and xy (discouraged). The 'button' parameter is never mentioned, leaving its accepted values (left/right/middle) undocumented anywhere.
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 ('Click') and resource ('a page element') and signals its browser scope, which separates it from mac_click and phone_tap. It does not explicitly distinguish itself from browser_fill/browser_type, which also target page elements, so sibling differentiation is only partially achieved.
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?
Gives an explicit preference ordering: element_index first, selector as fallback, xy not recommended. It also names the prerequisite source (latest browser_snapshot) and the validity window, leaving nothing about when/how to choose an input to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.