性能指标

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

With no annotations present, the description carries the full behavioral burden, yet it only lists the metrics returned. It does not state that this is a safe read-only operation, whether it perturbs the page, what it costs to call, or what the response shape looks like.

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?

A single front-loaded sentence with no filler. Every clause enumerates a distinct metric class, so nothing could be cut without losing information.

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 zero-parameter, annotation-free read tool with no output schema, the description covers what is returned but not the return format, units, or nesting of the metrics. It is adequate but leaves the agent guessing about response structure.

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 takes zero parameters, so there are no argument semantics to document; baseline 4 applies. The description correctly spends its text on output content instead of inventing parameters.

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?

Names a specific verb (获取/get) and enumerates the actual resources fetched: Performance.getMetrics metrics, navigation timing, paint timing, and JS heap usage. This clearly distinguishes it from siblings like page_screenshot or network_list, though it never explicitly contrasts itself with any of them.

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?

No guidance on when to call this versus other diagnostics tools (page_errors, console_read, network_list). Usage is only implied by the tool name and metric list; there are no preconditions, alternatives, or exclusions.

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