nex_browser_snapshot

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

Annotations already declare readOnlyHint=true, and the description adds that refs are 'short-lived'—a critical behavioral detail for agents to act promptly. It does not describe output format or other limitations, but the added ref-lifetime context earns credit.

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?

A single, front-loaded sentence that conveys purpose and key behavior without redundancy. Every word earns its place.

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?

With no output schema, the description should explain what the snapshot contains and how to consume the refs. It implies an accessibility tree with actionable refs but does not specify return structure or integration with other tools, leaving the agent somewhat under-informed.

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?

The description offers no parameter semantics. Schema coverage is only 60% (pageId, target, sessionId have descriptions; boxes and depth do not), and the description fails to compensate for the unexplained booleans/numeric parameters.

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 uses a specific verb ('Capture') and clearly identifies the resource ('accessibility/ARIA snapshot') with a key differentiator ('actionable refs'). This distinguishes it from sibling tools like take_screenshot or get_text.

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 implies usage for accessibility introspection and subsequent actions via refs, but does not explicitly state when to prefer this over alternatives or mention exclusions. No when-not-to-use guidance is provided.

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