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

With no annotations, the description carries the full burden and delivers real behavioral context: no code executes, no write budget is spent, passing does not prove external truth or independent reproduction, and secrets must be excluded. It omits auth requirements and what the preview actually returns.

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 tight sentences, zero filler, with the core operation and its preview/non-execution guarantee front-loaded before the caveats. Every sentence 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?

For a 4-required-param, nested-object tool with no output schema, the description adequately covers safety and non-execution but fails to explain what the preview returns (pass/fail outcomes) and leaves half the parameters undocumented. Enough to call it, not enough to fully anticipate its behavior.

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?

Schema description coverage is only 50%, so the description should compensate for undocumented parameters, but it adds essentially no meaning beyond naming 'dataset/result'. It says nothing about the statement or checker/rules parameters beyond what the schema already conveys.

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 and resource ('check a supplied public dataset/result with the... DSL') and clarifies the mode as a non-publishing dry run. It distinguishes the preview nature from write operations like submit_submission, though it never names the closest sibling check_finding to disambiguate the pair.

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 phrase 'without publishing or spending write budget' implies this is a pre-flight/dry-run step, giving implied context for when to reach for it. However, it never explicitly states when to use this over check_finding or submit_submission, nor any prerequisites, leaving selection to inference.

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