render_stats

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

With no annotations, the description carries the transparency burden and meets it: it explains that the tool reads the real view tree, enumerates the exact metrics, and warns that reset=true zeros frame counters as a side effect. The behavioral contrast with describe_ui's viewport scoping is genuinely informative.

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?

Three compact sentences, each with a distinct job: enumerate outputs, differentiate from sibling, explain reset. No filler, and the most decision-relevant guidance is 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?

Since there is no output schema, the description must state what the tool returns — it does, with a concrete metric list and an interpretive hint about what the three numbers together argue. It also covers the reset behavior, so an agent can invoke it 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 schema already documents all three parameters at 100% coverage, so the baseline is 3. The description adds value by restating reset=true's purpose ('so the next call measures one specific interaction') and tying it to jank attribution, which helps an agent decide when to set it. It doesn't add much for package/serial, but none is needed.

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 a specific measurement operation with the metrics it returns (total views, render-node kB, jank percentage, frame-time percentiles, skipped frames), so an agent knows exactly what the tool provides. It also explicitly distinguishes itself from describe_ui, preventing sibling confusion.

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 states directly 'Use this — not describe_ui — to MEASURE a screen' and explains why describe_ui undercounts lists, giving a concrete decision rule. It also instructs when to pass reset=true, covering the main usage branch.

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