browser_snapshot

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

No annotations are provided, so the description carries full burden. It details the output structure (ok, url, title, etc.), error cases ('Browser not launched', incomplete snapshot), and implies read-only behavior. No contradictions.

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?

Description is in two parts (English then Chinese). The Chinese is redundant in purpose but adds usage guidelines and structure. Front-loaded well. Slightly verbose due to duplication, but still clear and organized.

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 zero parameters and no output schema, the description covers output format, error scenarios, and usage context completely. It provides an example and lists return fields. No missing critical information for a snapshot tool.

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 input schema has no parameters, so baseline is 4. The description explicitly states '参数：无' (parameters: none). No additional semantic value needed beyond schema.

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 captures a structured snapshot of the current page including URL, title, visible text, form fields, and buttons. It distinguishes from sibling tools like browser_screenshot (visual) and browser_dom (raw DOM) by focusing on structured data for AI targeting.

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 Chinese section explicitly lists when to use: before interaction to understand page structure, to get clickable list before locating elements, to view fields before form filling, and to record page state at breakpoints. This provides clear context and implies when not to use (e.g., not for visual checks).

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