browser_perf

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

No annotations are provided, so the description carries the burden. It discloses an important behavioral detail: 'SPA 导航不重置计时' (SPA navigation does not reset timing) and notes the output source URL. This adds useful context beyond a simple 'read' operation.

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 two sentences: the first lists the metrics, the second gives usage context and a caveat. Every sentence adds value with no fluff or repetition. It is well-structured and front-loaded.

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 the tool's simplicity (a read-only metrics collector), the description covers the key aspects: what metrics, when to use, and a behavioral caveat. However, the lack of clarity on the task_id parameter and the return value structure (no output schema) leaves minor gaps.

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 schema has one parameter 'task_id' with 0% description coverage. The description does not mention or explain task_id at all, leaving the agent to infer its meaning from the name or sibling tools. The description should have clarified what task_id refers to (e.g., the browser task/session ID).

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 reads page performance metrics and enumerates specific metrics (FCP/LCP/CLS/INP, TTFB, DOMContentLoaded, load, slowest 5 resources). This distinguishes it from sibling tools like browser_network or browser_snapshot.

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 provides a clear when-to-use scenario: '页面慢/加载异常时用它定位是后端慢(TTFB)还是资源重' (when page is slow/loading abnormal, use it to locate whether backend is slow or resources are heavy). It does not explicitly mention alternatives, but the context is sufficient.

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