browser_snapshot

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds useful context: the tool returns a viewport screenshot and fresh element references, and can optionally navigate to a URL. There is no contradiction with annotations.

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 a single concise sentence with strong verbs and no redundancy. Every clause contributes meaning, and it is front-loaded with the primary action.

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 descriptive annotations and a clear statement of purpose/output, the description is adequate. However, it lacks parameter semantics and explicit usage guidance, and there is no output schema to fall back on. For a two-parameter tool, this is a noticeable gap.

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 0% (no descriptions on url or wait_ms), and the tool description does not explain these parameters. While names are somewhat self-explanatory, the description does not clarify that url is optional (default null) or that wait_ms controls the wait time before snapshot. With low coverage, the description must compensate but does not.

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 action: 'Open a public URL or observe the managed Chrome tab' and specifies the output: 'returning a viewport screenshot plus fresh element references for visual interaction.' This distinguishes it from sibling tools like browser_read (text) and browser_status (status).

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 indicates when to use it: for visual interaction and obtaining fresh element references. It also implies two scenarios (open a URL or observe the current tab). However, it does not explicitly mention alternatives or exclusions, such as 'use browser_read for text content.'

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