invariance_eval_dataset_create

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

Annotations already communicate readOnlyHint=false, destructiveHint=false, and openWorldHint=true, and the description does not contradict them. The description adds that the dataset is reusable and holds example rows, but it does not disclose duplicate-name behavior, return value, persistence semantics, or permissions requirements. Given annotations cover safety basics, this is slightly above neutral but still leaves behavioral 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 a single sentence that front-loads the action and definition. There is no redundancy or filler; every part adds clarity about what the dataset is and why it is used.

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 one-parameter tool with full schema coverage and no output schema, the description adequately explains the core concept and use case. It leaves minor details unstated (e.g., what object is returned, whether names must be unique), but an agent has enough to correctly invoke it.

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 only parameter, body, is already documented with a schema description, required/optional fields, and an example, giving it 100% schema coverage. The tool-level description adds that the dataset drives experiments—useful context—but the parameter's exact JSON format is already fully handled by the schema.

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 names the specific action and resource ('Create a reusable eval dataset') and defines the resource as a 'named collection of input/expected example rows used to drive experiments'. This clearly identifies what tool does and distinguishes it from siblings like list/get/append example tools, though it does not explicitly name siblings.

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 no guidance on when to choose this tool over alternatives. It does not mention that this is the first step before appending examples, nor how it relates to eval_suite_create or eval_case_create. There are no prerequisites, exclusions, or alternative routing conditions stated beyond the implied 'use this to create a dataset'.

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