metrics

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

readOnlyHint=true already establishes that this is a safe read. The description adds the specific counters returned (JS heap, nodes, layout/style recalcs, script duration), which is useful context, but says nothing about snapshot timing, cost, or whether values are cumulative vs instantaneous.

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?

It is a single short sentence fragment with no filler, but the missing verb and lack of front-loaded action make it less usable than it is short. Conciseness here shades into under-specification.

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, the description is the only place the return content is described, and the parenthetical list does that minimally. It does not convey the shape of the response (object keys, units, or whether metrics are zero-cost to collect), which an agent needs to use the result correctly.

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 per the baseline this starts at 4. Nothing in the description is needed to explain inputs, and it doesn't waste space doing so.

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 names the resource (renderer performance counters) and enumerates what it covers, but gives no verb, so the agent must infer that the tool retrieves them. It also fails to distinguish it from close siblings like state and snapshot, which plausibly also expose runtime diagnostics.

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?

There is no statement of when to call this instead of state, snapshot, or console. The agent gets no signal about whether this is for performance profiling, debugging, or health checks.

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