browser_act

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

The description adds context about the tool being 'AI-powered' and lists interaction types, which helps the agent understand it's an autonomous agent. However, it doesn't disclose potential failure modes, session lifecycle, or that the action might be non-deterministic. Since annotations already indicate not read-only, this is acceptable but not detailed.

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 exactly two sentences plus a cost note. It front-loads the core purpose and gives a clear usage condition. No wasted words, and the cost is a useful extra signal for the agent's decision-making.

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 3 parameters and no output schema, the description covers the essential context: what it does, when to use it, and even cost. It could mention return behavior or limitations, but it is largely complete for selection purposes.

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 fully documents url, max_steps, and instruction. The description adds no parameter-specific details beyond what's in the schema, so a baseline score of 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 clearly states the tool's purpose: 'Perform an action on a web page using AI-powered browser automation.' It enumerates specific action types (click, type, navigate) and 'interact with a page,' which distinguishes it from sibling tools like browser_extract or browser_validate.

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 provides explicit guidance on when to use: 'Use when you need to click, type, navigate, or otherwise interact with a page.' This gives clear context for use, though it does not explicitly mention alternatives that handle extraction or validation, so it falls 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.