wrave_click_and_read

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

With no annotations provided, the description carries the burden. It reveals that the tool returns the updated page snapshot in 1 turn, indicating a combined click-and-read behavior. However, it does not disclose edge cases such as what happens if the element is not found, whether the click triggers navigation that may invalidate the snapshot, or how the snapshot format relates to wrave_get_snapshot. This is a moderate disclosure level; it states the primary behavioral trait (returns snapshot) but lacks depth on error handling or side effects.

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 concise sentence that front-loads the core action (click) and includes key details (selector types and immediate snapshot). It is efficient with no wasted words. The structure is clear, though it could have separated the description of click and read behaviors for even better clarity.

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 no annotations and a moderate complexity tool with four parameters, the description covers the basic behavior and return value type (snapshot) but omits important context: error handling, whether the click may navigate to a new page, the relationship to wrave_get_snapshot for persistent snapshots, and any timeouts. It is sufficient for an agent to attempt the tool, but not fully complete for robust use.

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 documentation covers all parameters (100% coverage), so the baseline is 3. The description adds some value by explicitly listing the selector types (selector, @ref, x/y), which aligns with the schema and may help an agent understand that x/y are alternative coordinate-based inputs. However, it does not explain the interaction between selector and x/y (e.g., precedence, mutual exclusivity) beyond what the schema implies, so the description does not significantly enhance parameter semantics.

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 identifies the action (click an element) and the resource (a rendered page), and mentions multiple selector types (selector, @ref, x/y) and the return of an updated snapshot. It is distinguishable from siblings like wrave_click and wrave_double_click by noting the immediate snapshot return, though it could be even more specific about its role relative to the standalone wrave_click tool. The verb is specific and the resource is implied, so it earns a 4.

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 implies a usage pattern: clicking an element and then reading the resulting snapshot in the same turn. However, it does not explicitly say when to use this tool versus alternatives like wrave_click followed by wrave_get_snapshot or wrave_type_and_submit. The mention of 'in 1 turn' suggests efficiency, but no explicit when-not-to-use guidance or alternatives are named, so only implied usage is present.

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