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

Annotations already flag destructive, non-idempotent, and open-world behavior, but the description adds important operational detail: steps run once per call and are not retried, and a failed step returns the failing step plus the page HTML at that point. It also discloses that billing is one request, giving the agent context beyond the 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?

The description is front-loaded with the core behavior, then adds selector discovery, safety exclusions, failure semantics, and billing in focused clauses. The parenthetical action examples slightly duplicate the enum, but they serve as a useful quick capability summary.

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 complex, destructive, open-world browser automation tool with no output schema, the description covers purpose, execution model, safety limits, failure return shape, and billing. The agent has enough context to invoke it correctly, while the fully described schema supplies the parameter details.

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 100%, so the schema already documents each parameter in detail. The description still adds step-level meaning by saying steps are ordered, non-idempotent, and not retried; it does not add much for wait_method, wait_value, or proxy_country beyond the schema.

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 specific verb-resource pair: load a web page in a real browser, run ordered browser actions, then return the resulting HTML. It distinguishes the tool from read-only fetch siblings by emphasizing real-browser interaction and post-action HTML capture.

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?

It explicitly routes selector discovery to list_elements and gives a clear when-not rule: never use steps to buy, post, delete, or change anything unless the user asked for exactly that. It stops short of naming fetch_html or fetch_markdown as the simpler alternative for non-interactive retrieval, so the main sibling comparison is left implicit.

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