jev_browser_run

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

No annotations are present, so the description carries the full burden, and it does so thoroughly. It discloses live-Jev-only execution (never a fallback LLM), exact authorization semantics for action_rules, explicit verification through completion_text/completion_url, and specific stopping conditions including stale observations, repeated actions/pages, errors, and budgets.

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 dense and front-loaded, opening with the core pipeline and then adding only high-value constraints. Every sentence earns its place: authorization rules, supported actions, model behavior, verification, and stopping conditions. There is no filler or repetition.

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 9-parameter tool with no annotations and zero schema coverage, the description covers stopping behavior and constraints well, and an output schema exists so return values need not be described. Still, key invocation details remain unclear, such as what target_id refers to and how min_confidence and the timeout parameters behave. It is adequate but not fully complete.

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 does add real meaning for action_rules (exact role/name/action rows, explicit fill value) and for completion_text/completion_url (success verification). However, it leaves several parameters unexplained, including goal, target_id, max_steps, timeout_s, min_confidence, and total_timeout_s, so compensation is only partial.

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: it runs the observe → Jev → execute loop in one persistent Aside REPL session and explicitly names the supported action types (click/focus/fill). It does not directly contrast with siblings like jev_step or jev_validate, but the 'one persistent session' and full-pipeline language make its role reasonably distinguishable.

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 useful constraints that imply when the tool is appropriate: action_rules must be explicitly authorized, only click/focus/fill are supported, and live Jev is used. However, it offers no explicit guidance on when to prefer this tool over the sibling step tools, nor any exclusion criteria such as 'use jev_step for debugging individual actions.'

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