plasticity_analyze_cohesive_interface

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

With no useful safety signal from the annotations beyond readOnly/destructive flags, the description carries heavy behavioral detail: exports STEP, builds a conforming cohesive mesh, runs a 'pinned network-disabled Code_Aster solver', checks the Plasticity revision before and after solving, and saves an immutable report. It also discloses important interpretation caveats, e.g. that V3 means different things for CZM_EXP_REG vs CZM_LIN_REG, and that the result 'does not establish strength, design adequacy or print approval'.

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 content is largely substantive given the 20-parameter, multi-mode tool, and the purpose is front-loaded. However it is delivered as one dense run-on block with no headings or paragraph breaks, mixing prerequisites, axis-alignment rules, solver internals, and result-semantics caveats, which makes it hard to scan. Some sentences repeat the same-material/single-process constraint, so it is longer than strictly necessary.

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?

There is no output schema, so the description should cover what comes back; it does partially, disclosing the STEP export, immutable saved report, V3 labeling semantics, and the scope limitation on the result. Given the heavy nested schema it also explains the key mode-dependent requirements. The main gap is that it does not fully enumerate all input semantics, but for a tool this complex it is close to sufficient.

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 20 parameters, so the description must compensate, and it covers a great deal: it explains modeILaw defaults, useOrthotropicBulkProperties behavior, the poissonRatio/evidence requirement, the mixedModeRecordIds plus initialStiffnessEvidence.materialProcess and prescribedDisplacementGlobalMm alignment rules, and support/load face currency. It leaves some parameters (increments, meshSizeMm, adhesionPenalty, residualStiffnessRatio, splitPlanes format) unaddressed, so it is strong compensation but not exhaustive.

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 opening sentence names a specific verb and resource ('Run an experimental cohesive solver response for one current native Solid split by 1..255 ordered parallel planes into bulk regions') and immediately scopes it to a single same-material interface. It also explicitly distinguishes itself from adjacent work by rejecting dissimilar-material/multi-material prints and naming plasticity_plan_cohesive_layer_planes as the required prerequisite. An agent can tell it apart from plasticity_analyze_static_fem or plasticity_cohesive_fem_report without opening the 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?

It gives strong conditions for legitimate use: 'Every new analysis requires a profile-bound layerPlanePlan created by plasticity_plan_cohesive_layer_planes; arbitrary unbound split planes are rejected', and it states which law is the default versus which must be explicitly selected (CZM_EXP_REG vs CZM_LIN_REG) and when the Turon route applies. It also gives clear exclusions (dissimilar materials, mixed-mode prerequisites). It stops short of comparing against sibling analysis tools explicitly, so a 4 rather than 5.

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