browser_overview

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It discloses that selectors are CDP-generated snapshots (must re-call after page changes), input text shows hint instead of typed value (with workaround), error codes like BrowserNotConnected, and the silent fallback of non-matching scope. This is thorough and transparent.

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 well-structured: main purpose, usage suggestion, scope limit, return types, then caveats. Every sentence adds value. It is fairly concise given the amount of detail, though it could be slightly more streamlined. The front-loading of key usage before details is effective.

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?

Given 8 parameters, no output schema, and no annotations, the description handles purpose, usage, caveats, error codes, and return structure (elements with selectors, text, viewport status, ARIA state). It is almost complete, though the exact response format (e.g., array of objects) is implied rather than explicitly stated.

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 baseline is 3. The description adds value by explaining the silent fallback of the 'scope' parameter and the behavior of 'includeContext' and 'include' (though briefly). However, it doesn't elaborate on all parameters beyond the schema's own descriptions, but the added context about scope behavior is significant.

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 lists interactive elements with CSS selectors, visible text, and viewport status. It distinguishes itself by recommending use before browser_click to discover stable selectors and preferring it over screenshot for structured output, thus providing specific verb+resource and differentiation from siblings.

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 states when to use this tool (before browser_click, for verifying button/toggle state after submission) and provides alternatives (screenshot, browser_eval for actual typed content). It also gives explicit caveats about re-calling after navigation and silent scope fallback, offering complete usage guidance.

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