browser_evaluate

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

Annotations already carry the risk profile (destructiveHint=true, openWorldHint=true), so the agent knows arbitrary JS execution can mutate state and have external effects. The description adds the 'page or element' scope but doesn't disclose specifics like navigation side effects, error behavior, or page mutation consequences. No contradiction with 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?

A single front-loaded sentence with zero waste states the core action efficiently. It borders on under-specification since it almost duplicates the title, and one extra sentence distinguishing it from run_code_unsafe would have made it stronger, but as written it is appropriately terse.

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 annotations are rich and schema coverage is complete, so the description only needs to fill remaining gaps — but it doesn't. The key omissions are the relationship with browser_run_code_unsafe and behavioral outcomes of JS execution (errors, side effects, return format beyond what the filename param notes). Adequate but with a clear gap for a tool of this complexity.

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 100%, so the schema fully documents all four parameters — including a clear format for function ('() => { /* code */ } or (element) => { /* code */ }') and the filename/return-behavior note. The description itself adds no parameter meaning beyond what the schema provides, so the high-coverage baseline of 3 applies.

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 uses a specific verb and resource — 'Evaluate JavaScript expression on page or element' — clearly stating that it executes JS in the page context or against an element. However, it does not differentiate from the sibling browser_run_code_unsafe, which also executes JavaScript; an agent cannot tell the two apart from the description alone.

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 offers no guidance on when to use this tool versus alternatives. It never mentions browser_run_code_unsafe or the safe-vs-unsafe distinction, nor does it suggest when evaluating JS is preferable to the dedicated interaction tools (click, type, fill_form). The agent must infer usage entirely from the schema and hints.

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