browser_preview

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

With no annotations, the description carries the behavioral burden. It transparently indicates a non-mutating capture action ('Captures') and discloses the output: PNG, URL, title, scroll, and dimensions. It does not explicitly state that it does not alter the page or what happens if no browser is open, but the action is clearly read-only in intent.

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?

Two sentences with no real filler. The parenthetical '(the AI sees the page)' is slightly redundant with 'visual inspection tool,' but it reinforces the purpose and the description remains compact and front-loaded with the core capture behavior.

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?

For a parameterless screenshot tool with no output schema, the description adequately covers what is returned (PNG plus metadata) and when to use it. It is slightly incomplete in not mentioning prerequisites like an already-open browser, but that is a minor gap given the simplicity of the 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 tool has zero parameters, so the baseline is 4. The description correctly adds no unnecessary parameter detail and instead focuses on what output is produced, which is exactly what matters for a no-argument tool.

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?

Uses a specific verb ('Captures') with a clear resource ('current viewport as a PNG image') and enumerates the extra metadata returned. It also labels itself as 'the main visual inspection tool,' which clearly positions it relative to sibling inspection tools like browser_eval and browser_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 phrase 'main visual inspection tool' gives clear context for when to use it: whenever the agent needs to visually inspect the rendered page. However, it does not explicitly name alternatives or exclusion criteria, such as 'use browser_eval for DOM-level inspection instead.'

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