Contact Setup

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

Annotations indicate readOnlyHint=false, destructiveHint=false, but that's minimal; the description adds key behavioral context: it promotes CCX contact/nonlinear flags the FEM path already exposes, meaning no new solver is created. It also clarifies the gate relationship (bonded model is stiffer and less peak displacement), which helps the agent understand the physical behavior of the results. It doesn't mention whether it modifies the existing analysis in place or creates a new contact object, but the 'promotes the flags' phrasing gives some insight.

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 two paragraphs, but every sentence is informative: the first paragraph explains the operation and parameter details; the second provides post-requisites and a physical interpretation. It is front-loaded with the core action and delivers the most critical usage guidance. No filler words; it is concise yet complete.

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 the tool's complexity (6 params, no output schema, nested objects in face_pairs), the description provides enough to call it correctly: it explains the face_pairs structure, parameter defaults, the effect on the solver, the post-requisite sequence, and a relational gate for interpreting results. It even mentions the return value structure ('Returns {contacts:[handles], n_pairs, friction, nonlinear}') so the agent knows what to expect. There is no critical missing information.

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 description coverage, the description must compensate, and it does. It explains the semantics of `face_pairs` (list of {a:{handle, tag|face}, b:{handle, tag|face}} master/slave pairs), `friction` as Coulomb coefficient (0=frictionless), `slope` as penalty contact stiffness, and `nonlinear` default True sets GeometricalNonlinearity. It also notes the `analysis` parameter is in the schema but not explained; however, the name itself is clear. This is strong compensation for the schema gap.

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 states a specific verb ('Set up'), a clear resource ('surface-to-surface contact between face pairs for a CalculiX solve'), and explicitly mentions it flips the solver to nonlinear. It also distinguishes itself from a new solver setup, which differentiates it from sibling tools like fem_set_solver and fem_run. The purpose is unambiguous.

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 explicit sequencing guidance: 'Run fem_run + fem_results after.' It also provides a relative gate ('Gate RELATIVE to a bonded reference on the same mesh'), indicating when to use this in comparison to a bonded assumption. However, it does not explicitly state when not to use this tool or name alternative tools (e.g., fem_set_solver) for setting nonlinearity separately, but the context is clear enough for an agent to infer usage.

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