Do a task on the page (fast)

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

With no annotations, the description carries the burden well: it discloses that the agent clicks, types, and selects, runs at about 0.4 s per step, only types text present in the goal, and returns each step plus where it ended. It does not discuss failure modes, permissions, or side-effect reversibility, but the operational behavior is unusually well explained.

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?

Front-loads the core action, then supplies examples, timing, input constraint, return behavior, and prerequisite in a compact sequence. Every sentence adds actionable information without padding.

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?

Covers the essential context for a no-annotation, single-parameter automation tool: what it does, how to prepare the page, how to supply values, and what it returns. It could mention failure handling or confirmation behavior more explicitly, but the definition is complete enough to invoke correctly.

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 single goal parameter is fully covered by the schema, and the description adds a crucial constraint beyond the schema: every value to type must be included in the goal because it only types text that is in the goal. That materially changes how an agent should construct the parameter.

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?

States a specific verb and resource: hand a multi-step task on the current web page to VisionCLI's Jev agent. The examples (fill a form, search and open, set filters, add to cart) make the scope concrete and distinguish it from atomic siblings like browser_click or browser_fill.

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?

Clearly indicates multi-step tasks and gives prerequisites: open the right page first with browser_open, and check the result with browser_read if needed. It does not explicitly say when to prefer atomic browser_* tools over this one, so the alternative boundary is implied rather than fully stated.

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