create_fsi_project

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

With no annotations, the description carries the full burden and does so well: it names every file written (ProjectParameters.json, fluid.mdpa, etc.), the five required Kratos applications, the ALE/Dirichlet-Neumann coupling behavior, and a concrete divergence condition. It falls short of 5 only because it is silent on overwrite/existing-directory behavior and return semantics.

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?

Dense but information-rich, front-loaded with the core purpose before elaborating geometry, meshing, coupling, side effects, and dependencies. Length is largely justified by the tool's complexity, though the single unbroken paragraph lacks visual structure for such a long definition.

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?

A rich output schema exists, so return values need not be explained, and the description supplies the dependency list, generated artifacts, and physical validity caveats an agent needs to call it correctly. The remaining gaps are the undocumented parameters and the absence of explicit sibling-selection guidance.

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 must compensate, and it does substantially: it gives meaning to ramp_time, the [nx, ny] shape of fluid_divisions/wall_divisions, the accelerator option list, and couples wall_thickness/viscosity/length/E/fluid_height/time_step into a scaling relation. It leaves end_time, output_interval, dynamic_structure, poisson_ratio, wall_density, fluid_density, and max_coupling_iterations completely undocumented, so compensation is partial rather than complete.

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?

States a specific verb ('Scaffold') and a precisely defined resource: a partitioned FSI case with explicit 2D channel and elastic-wall geometry. It is unmistakably distinct from siblings like create_project, create_multistage_project, and create_cosim_project, which an agent can identify without opening any 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?

Usage is implied by the tool name and the 'runs with run_simulation like any case' workflow pointer, and the stability caveat implicitly warns when NOT to expect success. However, it never explicitly says when to pick this over the sibling creators (create_project / create_multistage_project / create_cosim_project), leaving the selection decision to inference.

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