Execute a named browser sequence, re-resolving elements after clicks or navigation, with optional expected URL/text polling. Use once instead of observing each page.
Run a named sequence. Prefer name (role/near) over uid. A name must bind uniquely. Re-resolves after click/navigate. Optional expectUrl/expectText poll. Call once instead of observe-per-page.
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes |
Changes observed during successful MCP inspections.
v0.2.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint: true, so the description does not need to repeat destructiveness. The description adds behavioral details such as 'Re-resolves after click/navigate' and 'Optional expectUrl/expectText poll,' which go beyond the schema. However, it does not explain the implications of destructiveness, failure behavior, or return format, so it only partially discloses behavior.
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 concise, with five short sentences each carrying a distinct piece of information. It front-loads the purpose ('Run a named sequence') and avoids redundancy. There is no fluff, making it efficiently structured.
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?
The tool is complex (runs a sequence) with a minimal schema and no output schema. The description does not explain the format of steps, available actions, or return values. It mentions expectations but not how to specify them, and it lacks error-handling or timeout information. This is insufficient for an agent to call the tool correctly without additional context.
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 0%, so the description must compensate. It adds meaning by explaining the preference for name over uid and the uniqueness requirement, which are not in the schema. It also hints at step behavior (re-resolving, polling). However, it does not fully describe the structure of the 'steps' array or the available actions, so it only partially compensates for the missing schema descriptions.
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 states a clear verb and resource: 'Run a named sequence.' It distinguishes from alternatives by saying 'Call once instead of observe-per-page,' and clarifies that it executes a pre-defined flow with naming preferences. This is not a tautology and provides specific, actionable information.
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 gives explicit usage guidance: 'Prefer name (role/near) over uid' and 'A name must bind uniquely,' which directs parameter construction. It also advises 'Call once instead of observe-per-page,' indicating when this tool is preferable. However, it does not explicitly state when not to use it or compare to other sibling tools like click/type, so it lacks full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.