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

Annotations already declare openWorldHint=true and destructiveHint=false, so the network-touching but non-destructive profile is covered. The description adds useful context (sandbox Chromium, screenshot() attaching PNG stills to the result), but says nothing about failure behavior, timeouts, or what a passing vs failing run returns for an arbitrary-code tool.

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?

Three tight sentences with the core action front-loaded and zero filler. The screenshot sentence partly duplicates the code parameter's schema description, which is the only redundancy.

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 and five parameters, the description should say more about what comes back besides attached screenshots (assertion results, console output, error reporting). It is adequate to invoke the tool but incomplete for interpreting results.

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 only 40%, so the description must compensate. It does add real meaning for base_url (defaults to local preview) and for code (screenshot capture), but timeout_ms and title get no explanation anywhere, leaving half the surface underspecified.

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?

States a specific verb and resource: run Playwright checks against the preview in a sandbox Chromium. That clearly separates it from file/config siblings, though it does not explicitly contrast with the code-execution siblings like bash or bash_await, which could also run scripts.

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 one concrete rule given is 'Omit base_url so it uses localhost,' which is a usage instruction for a parameter rather than for the tool. There is no statement of when to choose browser_run over bash/bash_await or what prerequisites (preview running, project context) are needed.

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