rush_benchmark

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

With no annotations, the description carries the full burden, and it does add useful behavioral context by noting the cache-write requirement for baseline recording and the returned shape {status, findings[], summary}. It does not explain side effects of other allow_* permissions, how thresholds are applied, or what happens in 'record' vs 'check' modes, so it is only partially transparent.

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 a single front-loaded sentence with no filler, and it packs the core action, a key prerequisite, and the result shape into a compact string. Every clause earns its place.

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?

Despite having an output schema, this is a highly parameterized tool with 14 inputs and no annotation support. The description leaves too much undefined for correct invocation: operation values, threshold semantics, samples handling, and the meaning of the many allow_* flags are all absent.

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 covers 0% of the 14 parameters with descriptions, so the description needed to compensate. It only clarifies <path> and the allow_cache_write requirement; the remaining 12 parameters (options, operation, samples, threshold_percent, baseline_name, etc.) receive no semantic explanation.

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 action ('Compare performance samples against baseline thresholds') and a target resource (<path>), so an agent can tell this is a benchmarking/regression-checking tool. It does not explicitly differentiate it from related siblings like rush_load or rush_snapshot, but the core behavior is clear.

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?

The purpose implies when to use it (when performance samples need to be compared to baseline thresholds), and it adds one operational prerequisite: baseline recording requires --allow-cache-write. However, it gives no explicit guidance about when not to use it or which sibling tool might be more appropriate.

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