interact

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

With no annotations, the description carries the full burden and does well: it reveals that the tool performs actions, returns newly triggered console errors, and warns about native dialogs that can block automation. It does not disclose failure modes or navigation side effects, but it provides meaningful behavioral context beyond the schema.

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 concise sentences, front-loaded with the core purpose, followed by the return value and a key caution. Every sentence earns its place with no repetition or filler.

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 tool is moderately complex and has no output schema, but the description covers intent, example actions, return behavior, and a critical pitfall. It does not spell out what happens on selector failure or navigation changes, but for its scope the description is close to complete.

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 already documents 'action', 'selector', and 'value' formats. The description adds context for why parameters are used but no new parameter-level detail; the baseline 3 is appropriate.

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 clear purpose ('Drive the page to reach a state worth inspecting') with concrete examples ('open a menu, submit a form, scroll to a section'). It distinguishes itself from the mostly observational sibling tools by emphasizing that it performs page actions rather than reading or capturing state.

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 clearly indicates when to use the tool: when the page needs to be manipulated into a state worth inspecting. It also gives an explicit exclusion ('Avoid elements that open native alert/confirm dialogs'). It does not name alternative sibling tools, but the context makes the action-versus-inspection split reasonably clear.

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