create_dataset

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

No annotations are supplied, so the description carries the full burden and does well: 'Replays nothing and costs nothing' rules out execution side effects and billing, and 'A Session sent twice becomes one test case' discloses dedup behavior. Gaps remain around name uniqueness/validation and what happens on partial failure, but the core behavioral profile is disclosed.

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?

Front-loaded with the action and cost/replay disclaimer, then the input rules, then next steps — a good order. The trailing ':param name:'/' :param test_cases:' lines restate what the prose already conveyed, which is mild duplication but not damaging.

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 3-parameter, non-annotated mutation tool with no output schema, the description covers what is created, the exclusivity rule, dedup behavior, cost, the return value, and the follow-up call. Only edge cases (name collisions, validation errors) are unaddressed.

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?

Top-level schema coverage is 0% (no descriptions on name/test_cases/pipeline_name), so the description must compensate, and it does: it defines name, states pipeline_name is required when a test case carries a session_id, and defaults test_cases to none. It also clarifies the session_id-vs-inputs exclusivity and expected semantics that the schema only partially documents in $defs.

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?

Opens with a specific verb+resource plus scope: 'Creates a Dataset, optionally with its first test cases.' It also implicitly separates itself from siblings by pointing to add_test_cases for later additions and create_experiment for running, so an agent can distinguish it from update_dataset/get_dataset/add_test_cases without opening a schema.

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?

Explicitly routes the agent: find Sessions with list_sessions, use add_test_cases to extend an existing Dataset, and create_experiment with the returned dataset_id to run it. It also states the mutually exclusive input rule (session_id or inputs, never both), which is the main selection decision the agent has to make.

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