Run a multi-step interaction sequence

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

With no annotations, the description carries the full burden. It discloses key behaviors: returns ONE screenshot plus ONE layout audit after the final step, failure semantics (gesture/wait aborts at index, expect_* fails but flow finishes and marks whole response a FAILURE), and performance note ('far cheaper'). It also clarifies evaluate_script reads page state without a screenshot. It omits some details like reflow pauses and permission requirements, but covers the most critical behaviors.

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 dense but every sentence contributes: purpose and cost in the first clause, capability overview in the second, and failure semantics in the third. It's front-loaded with the most important distinction (cheaper than chaining) and uses concise, scannable language. No filler or redundancy.

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 tool with nested steps, no output schema, and no annotations, the description covers the essential contexts: what it returns, failure modes, performance trade-off, and the range of actions. It doesn't detail the layout audit structure or explicitly mention the reflow pause (that's in schema), but the core agent-facing information is present. Slightly more detail on expected output shape would elevate it, but it's sufficient.

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 parameters are well-documented. The description adds meaning by explaining the overall flow: steps run back-to-back with a reflow pause, failure modes per step type, and the aggregate output. It also clarifies the action enum's relationship to interact_and_audit and the pointer_* actions' purpose for canvas/shadow DOM. This goes beyond the schema's individual parameter descriptions.

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 clearly states the tool is a batch pipeline for multi-step flows like forms and nested menus, with specific verbs (navigates, matches viewport, runs steps) and a distinct resource (multi-step interaction sequence). It explicitly differentiates from chaining interact_and_audit by highlighting cost efficiency, so an agent can immediately understand its role.

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 names the alternative (interact_and_audit) and explicitly says it's 'far cheaper than chaining' that tool, giving clear context for when this tool is preferable. It also describes capabilities (mixing gestures, waits, expect_* and evaluate_script) but doesn't explicitly state when NOT to use it (e.g., for a single-step action), so it falls just short of a 5.

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