evaluate_js

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

Discloses side effects (DOM modification, state changes, network requests) and return behavior (awaits promises, returns serialized value or error). Lacks mention of synchronous error handling or CSP restrictions, but adequate without annotations.

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?

Five sentences, each providing distinct value: purpose, side effects, prerequisites, return value, usage guidance, and alternatives. Front-loaded and no waste.

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 purpose, prerequisites, side effects, return value, usage, and alternatives. With no output schema, explains return value. Minor gaps: does not address non-promise errors or content security policy restrictions.

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?

Single parameter with 100% schema coverage. Description adds context about return type and side effects but does not significantly enhance parameter understanding beyond the schema's own description of constraints and behavior.

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?

Clearly states it executes arbitrary JavaScript in page context and returns JSON-serializable values. Distinguishes from siblings like inspect_dom and click_element.

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?

Explicitly states when to use (dynamic inspection, DOM manipulation, complex interactions) and when not (alternatives provided). Also states prerequisites (active tab, script context).

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