launch_simulation

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

Beyond annotations, it discloses that the operation costs money, which is a critical real-world side effect. It also reveals the confirm workflow, the distinction between preemptible and non-preemptible instances, and the optional mesh reuse behavior. These traits are not derivable from annotations and materially affect an agent's invocation decision.

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 compact and front-loads the most important operational fact: 'Costs money.' Each parameter line earns its place by mapping to a schema property, and the confirm flow is stated in one clear directive. There is no filler or repetition.

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?

This is a 7-parameter, financially consequential tool with no output schema, yet the description covers every parameter, the approval workflow, cost implications, and resource sourcing from sibling tools. It even tells the agent to show the returned summary to the user, covering the immediate post-invocation behavior. Nothing essential is missing for correct call selection and execution.

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 0%, so the description carries full responsibility for explaining parameters. It explicitly maps solver to list_solvers, cpu/ram to suggest_resources or list_machine_options, folder to the storage case, mesh_folder to an optional mesh, and regular_instance to a more expensive non-preemptible machine. This compensates completely for the bare 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 opens with a specific verb and resource: 'Launch a simulation on a case folder already in storage.' It also distinguishes this from sibling tools like wait_for_simulation, stop_simulation, and list_simulations by emphasizing the launch action and cost. The phrase 'already in storage' clarifies the prerequisite state without ambiguity.

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 gives clear operational guidance: how to pick solver, cpu/ram, folder, mesh_folder, and regular_instance, and where to source those values from sibling tools. It also prescribes the two-call confirm flow with explicit user approval. It does not mention when not to use this tool, but the instructions are otherwise explicit and actionable.

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