Diagnose performance

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses a great deal: the shape of findings (evidence ids, strength, fix), the 'healthy' and 'unknown' sentinel states, explicit blind spots (no CPU sampling, no widget rebuild counts), and the caveat that GC correlation strength is bounded by frame coverage of the window. This is unusually rich behavioral disclosure that annotations cannot carry.

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 long description, but it is front-loaded with the core proposition ('why... not just how much') and every subsequent clause adds distinct information about outputs, states, or limits. Density is high enough that the length is mostly justified, though it could be trimmed slightly.

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?

There is no output schema, so the description bears full responsibility for describing returns, and it does: percentiles, build-vs-raster split, correlated findings with evidence ids/strength/fix, plus healthy/unknown semantics and explicit limitations. An agent has everything it needs to interpret results.

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 the baseline of 4 applies and there is no parameter semantics to clarify. Nothing in the description contradicts or undermines this.

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 states a specific verb and resource and sharpens the scope with the contrast 'why the app is janky, not just how much,' which implicitly separates it from raw measurement tools like get_frames. It does not name any sibling explicitly, so an agent must infer the boundary from the 'why vs how much' framing rather than a direct reference.

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?

Usage context is clear: reach for this when you need causes rather than magnitudes, and the 'healthy'/'unknown' states tell the caller when the output is trustworthy versus noise. There are no explicit exclusions or named alternatives, so routing against diagnose_runtime or get_frames is left to inference.

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