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

With no annotations, the description effectively communicates the non-interactive behavior (no coordinates, no scrolling) and error conditions (non-interactable or stale elements). It covers the key behavioral traits an agent needs to know.

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 well-structured, with the core action and requirements front-loaded. Each sentence adds value: identifies the element source, clarifies the protocol behavior, notes cross-platform support, and lists failure modes with remediation. No fluff.

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 tool with a simple schema (2 params) and no output schema, the description covers the essential context: what it does, how it behaves, and how to handle errors. It could add information about the return value (e.g., success status) but that's a minor gap.

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 already has 100% description coverage for both parameters (elementId and sessionId), so the description adds minimal extra meaning. It reinforces the origin of elementId (from session_find_element) but doesn't provide new semantic details.

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 clearly states it clicks an element found by session_find_element, specifying the required identifiers (elementId and sessionId) and the mechanism (WebDriver protocol). It distinguishes itself from coordinate-based taps on real devices (device_tap, ios_tap).

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?

It explicitly states when to use this tool (for browser and mobile sessions via WebDriver) and when not to (for coordinate-based taps on real devices, pointing to alternatives). It also provides error handling guidance, advising to re-find the element and retry if stale.

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