Đo lỗi tràn ngang ở viewport hiện tại

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

No annotations are supplied, so the description carries the full behavioral burden, and it discloses very little. It doesn't say whether a live browser session is required, whether the tool itself resizes the viewport (the description mentions desktop vs mobile but the only parameter is "project"), whether the operation is read-only, or what the response looks like. For an audit tool with zero annotation coverage this leaves the agent guessing about preconditions.

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 short sentences, front-loaded and free of padding. The second sentence is a bit oblique ("chỉ số tràn ngang" appears without having been introduced), but nothing is redundant or wasted.

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?

Placeholder note: completeness relative to a simple one-parameter audit tool is moderate; there's no output schema so return values needn't be explained, but the missing parameter documentation and the unexplained gap between "desktop or mobile" and a `project`-only schema mean an agent cannot fully predict call behavior. Score 2 is more accurate than 4.

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% for the single required parameter "project", and the description never mentions it at all – no explanation of what a project identifier is, where it comes from, or what format it takes. This is the one case where the description had to compensate for the schema and it does not. The description instead talks about viewport modes that have no corresponding parameter.

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 pairs a concrete action ("Đọc chiều rộng trang" – read page width) with a scope condition ("tại desktop hoặc mobile"), so the agent gets a rough sense of the tool. But it never states that the tool performs a layout/overflow audit, which is what the name and title imply – it reads more like a width-reading measurement. It's vague enough that distinguishing it from tester_browser_inspect or tester_browser_see takes inference.

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 second sentence gives one workflow hint – that overflow figures should be cross-checked against an image (likely tester_browser_see) to judge UI errors – which is genuinely useful context. However, there is no explicit when-to-use/when-not, no mention of tester_browser_accessibility_audit or tester_browser_security_audit, and no prerequisite stated (e.g. that a browser session and a chosen viewport must already exist). Usage is only implied.

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