perf_metrics

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

Annotations already declare readOnlyHint and idempotentHint, so the description's 'changes nothing' is reinforcing but not the main contribution. It adds valuable context beyond annotations: the data is read over CDP, it is Chromium-only, and it is cheap telemetry. These operational details help an agent understand platform and protocol requirements.

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 compact and front-loaded: the first sentence states the resource and values, the second gives the use case and alternative, and the third summarizes safety and platform constraints. Every clause earns its place with no redundant filler.

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 read-only tool with an output schema, this description is complete. It covers what data is returned, the operational context (CDP, Chromium only), the intended use case, and the safety profile. Nothing needed to select and invoke the tool correctly is missing.

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?

There are zero parameters and the schema is empty, so there is nothing to document; baseline 4 is appropriate. The description compensates by enumerating the kinds of data returned (DOM nodes, heap size, durations), which helps an agent understand what the tool actually provides.

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 Chromium performance counters for the current page, listing specific metrics: DOM nodes, JS heap size, layout and task durations. It differentiates itself from real profiling tools by framing itself as cheap telemetry and pointing to chrome-devtools for deeper profiling.

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?

It explicitly says when to use this tool: 'for spotting growth between actions', and gives the alternative: 'for real profiling use chrome-devtools.' The 'chromium only' constraint also sets clear boundary conditions for when this tool should not be used.

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