preview_experiment

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

No annotations provided, so description carries full burden. It clearly states the tool does NOT execute, only previews. It details the return JSON structure including resolved spec, total_runs, and time estimate derivation. No surprises.

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?

Well-structured with bullet points and clear separation of modes. Every sentence adds value, no redundancy. Front-loaded with the key purpose. Highly efficient.

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?

Given 11 parameters, no required ones, and presence of output schema, the description covers the essential aspects: two modes, what each returns, and the time estimate. No missing context for effective selection and 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 coverage is 0%, so description compensates well by explaining the two modes and which parameters to pass in each (experiment_name vs metrics + optional fields). However, it does not individually describe all 11 parameters (e.g., model_path, sequential_run_order). Still adds significant meaning beyond 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 clearly states the tool shows a run plan without executing, using the verb 'show' and resource 'run plan for a BehaviorSpace experiment'. It distinguishes from sibling 'run_experiment' by explicitly advising to use it beforehand.

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 says 'Use this before run_experiment to verify parameter combinations...' and describes two modes (by name and inline) with clear instructions for each. No ambiguity about when to use.

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