web_action

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

With no annotations, the description carries the burden of behavioral disclosure. It covers ordering, count limits, session isolation, tab-safety, and the fill field syntax. It doesn't explain error propagation, atomicity, or side effects of continue_on_error, but the guidance provided is far beyond a generic 'execute actions' statement.

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?

Three tightly packed sentences, with the core behavior first and operational guidance after. Every sentence earns its place; no filler or restatement of the name.

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 flexible tool that accepts 1-32 heterogeneous actions, delegating full action details to web_info action_schema is a sensible division of labor. The description includes the essential constraints and a concrete example. It is not fully self-contained, but it gives the agent a clear path to the missing details while the output schema covers return values.

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 0%, so the description must compensate. It does explain the fill action format (fields={CSS_selector: value}), which adds real parameter meaning. However, it does not explain the structure of the actions array items or the continue_on_error parameter, leaving substantial gaps.

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 opens with a specific verb and resource: 'Execute 1-32 ordered actions.' It adds critical scope details (count limit, ordering) that differentiate it from sibling web_info, which is clearly the informational/schema tool. An agent can tell what web_action does without inspecting the schema.

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 explicitly directs the agent to 'Read web_info action_schema before unfamiliar actions or after validation errors,' which effectively explains when to consult the sibling vs. act. It also gives operational constraints: use a unique session_id per task/agent and never close another agent's tabs. This is clear context, though it stops short of explicit 'use X instead of Y' phrasing.

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