recommend_setup

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It clearly states the tool returns a plan and, when inputs are missing, returns questions—so it discloses its core non-mutating nature and conditional behavior. It does not, however, describe edge cases (unrecognized goals), the exact output format beyond a list, or how it handles invalid combinations of parameters, leaving moderate 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 paragraph that front-loads the main purpose, lists deliverables in a natural flow, then adds the conditional behavior. Every sentence carries value—no filler, and the 'Start here' is a useful directive. It is appropriately sized for the complexity.

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?

The description is reasonably complete for a planning tool: it tells what it returns, how it handles missing inputs, and positions it as the entry point. However, it lacks details on how other parameters (fluid, transient, heat_transfer) influence the plan, and does not define the expected output schema (e.g., whether it returns a JSON object, text, or a numbered list format). Given no annotations or output schema, these gaps matter.

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?

With 0% schema coverage, the description must explain all parameters. It explicitly mentions only 'goal' (plain-language input) and 'velocity/length' (the ones that trigger questions). It gives no insight into 'fluid', 'transient', or 'heat_transfer', leaving the agent to guess their roles. This is a substantial deficiency given the lack of schema documentation.

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 specifies a clear verb ('Turn a plain-language goal into a complete setup plan') and lists concrete outputs (solver, turbulence model, target y+, blockMesh preset, fields, boundary conditions, step list). This distinguishes it from numerical calculators like y_plus_from_height or execution tools like scaffold_case, so an agent can immediately tell its role.

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 phrase 'Start here' signals this is the entry point for a planning workflow. It also explains that if velocity/length are missing it asks follow-up questions, guiding the agent to call it early. However, it does not explicitly name alternative tools (e.g., 'use list_solvers to see options') or state when NOT to use it, so it misses the 'when-not' clarity.

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