jev_benchmark

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

With no annotations, the description carries the full burden and does disclose key traits: the run is offline (no network), deterministic (reproducible results), and returns both accuracy and timing metrics. Gaps remain — it doesn't say whether the run writes any files, how long it typically takes, or what happens if input_path is missing — but the core behavioral profile is conveyed.

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?

A single front-loaded sentence that states action, key properties, and return values with no filler or redundancy.

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 must signal what comes back; it does so ('accuracy and timing metrics'). Combined with the offline/deterministic qualifiers, an agent has enough to call it correctly, though runtime expectations and side effects are unstated.

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?

Only one parameter and schema coverage is 100%, so the schema already documents input_path as the JSONL fixture path including its default. The description adds no extra meaning (e.g., accepted formats, whether relative or absolute paths are expected), matching the baseline for well-covered schemas.

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?

States a specific verb ('Run') and resource ('offline deterministic Layer-0 JSONL replay benchmark suite') and adds the return payload ('accuracy and timing metrics'). None of the siblings (jev_autopilot, jev_verify, etc.) overlap with a benchmark runner, but the description never names or contrasts an alternative, so it stops short of explicit sibling differentiation.

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 is only implied: an agent can infer this is the tool to invoke when it wants to measure Layer-0 replay performance. There is no explicit when-to-use, when-not-to-use, or prerequisite statement (e.g., whether the corpus must exist, whether results are comparable across runs).

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