score_benchmark_submission

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

With no annotations provided, the description must carry the full burden. It discloses the key behavioral trait that it reports two categories of errors separately and the reason, which adds value. However, it does not disclose output format, side effects, or how unknown verdicts are treated, leaving gaps.

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 two sentences, immediately stating the action and then providing a concise rationale for the report separation. No filler words.

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?

The tool is simple with one well-described parameter, and the description explains the main output distinction. However, without an output schema, it would be helpful to specify the return format or how UNKNOWN verdicts are handled, leaving some incompleteness.

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 provides full coverage of the single parameter, describing it as a mapping from fixture file name to verdict values. The tool description adds no extra parameter details beyond 'set of verdicts', so the baseline score applies.

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 clearly states the tool grades a set of verdicts against the benchmark, using the verb 'Grade' and specifying the resource. It distinguishes itself from siblings by focusing on evaluation of verdicts and explicitly separates unsound from imprecise verdicts, which no other sibling suggests.

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 description provides some context by explaining why unsound verdicts are reported separately ('because only the first kind ships a vulnerability'), but it lacks explicit guidance on when to use this tool versus alternatives like check_constant_time or find_leak. The usage is largely implied from the name and description.

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