generate_inputs

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

With no annotations, the description carries the full burden, and it does disclose two non-obvious traits: no license required, and that a 'generated' status means input export only, not a solved case. However, it says nothing about what is written to disk, whether existing files are overwritten, or what the confirmation_token gate implies — the most consequential behavioral fact for a write-ish export tool.

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?

Three short sentences, front-loaded with the output artifacts and followed by the license and workflow caveats; nothing is padding. Minor cost from the mid-sentence line break and undefined acronyms, but no wasted content.

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?

An output schema exists, so return values need not be explained, and the license/workflow caveats are covered. But for a tool whose sole required parameter is a large nested case config with zero schema descriptions, the definition leaves the agent without enough to construct a call or understand the confirmation step.

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% across an extremely deep config tree, so the description must compensate. It only implicitly maps to the geometry discriminator ('parametric ... or imported HST') and leaves the required config object, all its sub-objects, and especially confirmation_token entirely unexplained — an agent cannot tell from the text what that token gates or where to obtain it.

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 (export) and the concrete artifacts produced (MRI/HST, RDF, MCN, RAO), and the parenthetical '(or imported HST)' distinguishes the two geometry source paths. It also names the downstream sibling prepare_case, so the agent can place it in the workflow, though the domain jargon means an agent unfamiliar with HydroStar gains only partial clarity.

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?

Gives a clear sequencing rule ('use prepare_case before attempting any calculation') and a key precondition ('works without a HydroStar license'), which materially affects whether an agent should attempt it. It stops short of naming the alternative export/preparation siblings (build_geometry, make_reference_case, plan_case) or stating when not to use it.

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