Execute Script

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

With no annotations, the description carries the full burden. It discloses that execution targets the foreground page and returns a JSON result, but says nothing about side effects, permissions, whether it can hang on arbitrary JS, or error behavior for a powerful script-execution primitive.

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 zero filler; the verb and target are stated immediately.

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 2-parameter script-execution tool with no annotations and no output schema, the description omits the meaning of `device`, safety/permission context, and how errors or non-JSON returns are handled. It is too thin for the tool's power.

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 0%, so the description must compensate and does not. The `device` parameter is entirely unexplained — nothing tells the agent what a device identifier means here or that a null default targets the active device. Only the `js` parameter is loosely implied by 'run JavaScript'.

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 (Run/Execute) and resource (JavaScript in the foreground browser page), which distinguishes it from UI-interaction siblings like tap or ui_json. However, it does not cross-reference any sibling tool, so selection between it and other script/UI tools is left to inference.

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 indication of when to prefer running script versus using the dedicated UI tools (ui, tap_text, find_nodes), and no stated prerequisites or exclusions. The agent is given no routing guidance.

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