wait

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 disclose the core blocking behavior and the AND/OR semantics of conditions and events. However, it never states what happens on timeout (timeoutMs default 10000 implies a failure mode but it is not named), whether the operation is non-destructive, or how poll mode and event mode interact.

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 one front-loaded sentence that leads with the action verb and packs both operating modes into the first clause. It is appropriately compact. The trailing ellipsis ('notLoad…') signals a truncated list rather than deliberate conciseness, which is a minor structural flaw.

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 10 parameters, zero annotations, and no output schema, this description is substantially incomplete. It fails to cover event-mode values, the timeout/failure contract, and the semantics of selector and pendingDialogsGt. An agent cannot fully predict this tool's behavior from the description and schema alone.

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 description coverage is only 40%, so the description must compensate. It adds real meaning by explaining that urlContains, hasModal, hasCaptcha, and notLoading are conditions that are ANDed and polled — semantics the bare boolean/string schema fields do not convey. However, selector and pendingDialogsGt remain unexplained in both schema and description, and the event parameter's schema text is itself truncated.

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 uses a specific verb ('Block until') and names the resource: page conditions or page events. It enumerates concrete conditions (urlContains, hasModal, hasCaptcha) and states they are ANDed, which distinguishes this synchronization tool from action siblings like click, type_text, and navigate. However, the sentence ends truncated ('notLoad…'), leaving the full condition list unstated and the 'page event' branch vague.

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 the usage context: use it when a subsequent action depends on a page reaching a condition or an event firing, and it correctly conveys that conditions combine with AND. But it gives no exclusions, names no alternative sibling (e.g., status or read for non-blocking state checks), and offers no guidance on choosing between poll mode and event mode.

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