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

Annotations provide no readOnly/destructive hints, so the description carries full responsibility for behavioral disclosure. It reveals 'atomically' and a 20-step limit, but leaves out critical details such as what happens on step failure (rollback? partial execution?), session handling, authentication needs, or side effects of actions like click/type. The word 'atomically' is ambiguous and not elaborated, and the description lacks essential behavioral context for a mutation-capable automation tool.

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 two concise sentences, front-loaded with the core function and action list, with no fluff. Every word adds either specificity (multi-step, atomic) or useful limits (up to 20 steps), making it efficient and easy to parse.

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 tool with 4 parameters, low schema coverage, no output schema, and minimal annotations, the description is severely inadequate. It fails to explain the role of each parameter, execution context, error behavior, return value, or how steps interact, leaving the agent without essential information to correctly invoke the tool in complex scenarios.

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 only 25% (solely 'steps'), and the description does not compensate. It mentions the action types, but these duplicate the action enum from the schema and do not explain the meaning of `viewport`, `session_id`, or `persist_session`. The description adds no value beyond the schema for parameter semantics, leaving key parameters underdocumented.

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 'Execute' and clearly identifies the resource as 'multi-step browser workflow' with a list of actions (navigate, click, type, wait, scroll, screenshot, extract, evaluate). It distinguishes from sibling tools like scrape_webpage and screenshot_webpage by emphasizing multi-step and atomic execution, making the purpose unmistakable.

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 implies usage for multi-step workflows (e.g., 'multi-step browser workflow', 'Up to 20 steps') but does not explicitly state when to use this tool versus alternatives like scrape_webpage for single-page extraction or screenshot_webpage for single screenshots. No alternatives are named, so guidance is merely implied, not explicit.

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