Auto-Browser

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

Lacks annotations entirely, yet the description fails to disclose that this tool can perform high-risk operations (social posting, file uploads, payments, account changes) or explain what determines success/failure returns. Only behavioral hint is 'one' implying atomic single execution.

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?

Single sentence is appropriately brief, but wastes space on unhelpful internal jargon ('shared internal action schema') that conveys no actionable information to the agent. Not front-loaded with critical safety or usage constraints.

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?

Severely inadequate for a tool with 20+ distinct action types spanning navigation, social media manipulation, file uploads, and destructive operations. No output schema, no annotations, and 0% parameter coverage combined with minimal description leaves critical gaps.

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?

With 0% schema description coverage, the description completely fails to compensate. It does not explain session_id, the critical approval_id for risky actions, or the complex structure of the action object (which contains 20+ optional fields for different action types).

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?

States it executes 'one browser action' which conveys atomicity, but relies on vague jargon ('shared internal action schema') rather than explaining what kinds of actions are possible (navigate, click, social post, upload, etc.). Does not differentiate from specific sibling action tools like browser.drag_drop or browser.eval_js.

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?

Provides no guidance on when to use this generalized action executor versus specific action siblings (browser.click, browser.eval_js, etc.), nor when approval_id is required for risky operations like 'payment' or 'destructive' actions evident in the schema enums.

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