Waits until a specified element, text, or time condition is met in a browser page, helping automation pause reliably before the next action.
Wait for a target, text, or a bounded duration.
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | ||
| time | No | ||
| pageId | No | Defaults to the active page | |
| target | No | Snapshot ref (e12) or unique CSS selector | |
| timeout | No | ||
| sessionId | No | Defaults to the active session |
Changes observed during successful MCP inspections.
v2026.10.24Input schema / properties / pageId / descriptionPrevious value: -"Stable page ID; defaults to the session active page"New value: +"Defaults to the active page"Input schema / properties / sessionId / descriptionPrevious value: -"Optional session ID; defaults to this MCP client active session"New value: +"Defaults to the active session"Input schema / properties / target / descriptionPrevious value: -"Snapshot ref such as e12, aria-ref=e12, or a unique CSS selector"New value: +"Snapshot ref (e12) or unique CSS selector"v2026.8.14Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does not meet it: it does not say what happens on timeout (error vs. silent return), whether the call blocks, what a call with zero arguments does given all parameters are optional, or how the two duration controls interact. The distinction between the 'time' and 'timeout' parameters is never resolved.
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?
A single front-loaded sentence with no filler. The problem is under-specification rather than verbosity, but nothing stated is wasted.
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 six-parameter tool with no annotations, no output schema, and half its parameters undocumented, the description is far too thin. An agent cannot determine default behavior, failure modes, or parameter precedence from it.
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 only 50% (pageId, target, sessionId documented; text, time, timeout bare), so the description should compensate and does not. Critically, it never explains the difference between 'time' (bounded duration) and 'timeout', nor whether 'target' and 'text' are mutually exclusive or combined with OR 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 verb 'wait for' plus the three waiting conditions (target, text, bounded duration) tell an agent concretely what the tool does. No sibling tool competes for this role, so differentiation is unnecessary, though the phrasing is compressed enough that a reader must infer the intended ordering semantics.
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?
There is no statement of when to use this tool, when to use something else instead, or what prerequisites apply (e.g., call after navigate before snapshot). Usage is only implied by the word 'wait'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.