test_run_dataset

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does mention that no report is saved and that results are returned, which is useful. However, it omits critical behavioral traits such as whether the operation is read-only or mutating, whether it can be safely repeated, any side effects on the test or environment, or permission requirements. The lack of such disclosure for an execution tool is a significant gap.

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, information-dense sentence that front-loads the key concept ('Data-driven') and immediately states the core behavior, return type, and a notable exclusion (no report saved). There is no redundancy, fluff, or unnecessary detail. Every word contributes to understanding the tool's purpose and key differentiator.

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 tool with no output schema and no annotations, the description provides the core functional behavior but leaves out important contextual details. It does not describe the structure of the returned results, error handling, limits on rows, or any prerequisites like requiring a saved test. It also does not disclose safety or side effects, which is especially relevant for an execution tool. The description is adequate for a basic understanding but not fully complete for safe and correct invocation.

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 100%, so all parameters have descriptive text in the schema. The tool description adds a small amount of semantic value by clarifying that 'rows' represent overrides and that each row corresponds to one run, which aids understanding of the rows parameter. However, it does not elaborate on other parameters like env, browser, or stepTimeoutMs, so the added value over the schema is marginal. This aligns with the baseline of 3 for high schema coverage.

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 clear, specific behavior: runs a test once per row of overrides and returns per-row results plus totals. It differentiates from siblings like test_run by emphasizing the data-driven, multi-run nature and explicitly notes that no report is saved, which distinguishes it from report-related tools. This is a precise and non-tautological statement of purpose.

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 implies usage for data-driven scenarios ('Data-driven') and clarifies the behavior, but it does not explicitly state when to choose this tool over alternatives like test_run or test_validate. It lacks direct exclusions or comparative guidance, leaving the selection to inference from the name and description. There is no mention of prerequisites (e.g., a saved test must exist) or when not to use it.

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