Skip to main content
Glama

Impact Dynamics Submit

impact_dynamics_submit

Submit a transient drop/impact simulation of a meshed body against a rigid floor to predict peak force, stress, and failure criteria, returning a job for results.

Instructions

Transient DROP / IMPACT dynamics — the solve drop_impact escalates to. Meshes body, flies it at velocity_m_s (or the free-fall speed of drop_height_mm — exactly one) along direction into a fixed rigid floor through penalty contact, and integrates the motion with CalculiX *DYNAMIC. Async: returns a job — poll job_result. Degrades to {ok:false, reason, install} when ccx is absent.

direction is the way the part TRAVELS: '-z' (default), '+x', … or any 3-vector — [-1,-1,-1] is a corner drop (the floor turns, the part is not re-meshed). Material from material or explicit youngs_mpa/poisson/density_kg_m3 (required, no defaults — the answer scales with √(E·ρ)). yield_mpa arms the stress criterion; plastic=True (+ tangent_mpa, bilinear) lets it yield instead. deceleration_limit_g arms the fragility criterion. method: 'implicit' (default; HHT-α, ccx steps adaptively — right for ms-scale drops) | 'explicit' (central difference at the stable step — for stress-wave events ≲ 100 µs; first-order tets). time_step_s on an implicit run switches to a FIXED step: several times faster where contact comes on smoothly, but ccx stops if an increment diverges (a flat face landing all at once does). duration_s defaults to free flight + 10 wave round trips along the drop — enough for a stiff body; a compliant one needs more, and the gate says so. samples is the single output cadence ccx allows (force history AND stress frames; default sized to the mesh). contact: 'auto' (default) | 'face' | 'node' — measured: ccx's face-to-face penalty never engages a corner strike (the part falls through) and its node-to-face one locks up on a broad flat landing, so 'auto' uses face contact down to a 45° edge and node contact for anything sharper. engagement_lag_mm reports how far the strike point sank before the contact pushed back.

Validated against the exact St-Venant bar (bar_impact): face force ρ·c₀·v₀·A, contact duration 2L/c₀, restitution 1 and the plastic-wave cap all within ~1–3 %. A real part is banded (~20 %): peak force depends on the penalty stiffness and mesh, a stress peak AT the strike point is mesh-dependent, and a sharp wave front rings ~20 % high. No friction, failure or erosion.

Returns the degradation dict, or {job_id, status, cache_hit}; poll job_result for {ok, returncode, solver, case_dir, nodes, tets, method, direction, velocity_m_s, drop_height_mm, duration_s, time_step_s, mass_g, strike_node, contact_faces, contact, strike_alignment, plastic, bar_stress_mpa, peak_force_n, peak_force_median3_n, peak_force_time_s, peak_g, impulse_n_s, contact_start_s, contact_duration_s, separated, arrested, rebound_velocity_m_s, restitution, energy_end_ratio, energy_min_ratio, mass_check, samples, contact_samples, engagement_lag_mm, peak_von_mises_mpa, peak_stress_node, peak_stress_time_s, peak_stress_location_mm, force_history, gate} where gate is {pass, score, fidelity:"solve", band_pct, checks, utilisation, warnings} — a run that ends before the fall is arrested, or whose energy grows, FAILS.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "body": "<body>"
    },
    "name": "impact_dynamics_submit"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
gap_mmNo
methodNoimplicit
contactNoauto
gravityNo
plasticNo
poissonNo
samplesNo
materialNo
directionNo-z
workspaceNoRun this call in this named workspace
yield_mpaNo
duration_sNo
youngs_mpaNo
tangent_mpaNo
time_step_sNo
velocity_m_sNo
density_kg_m3No
char_length_mmNo
drop_height_mmNo
max_time_step_sNo
deceleration_limit_gNo
contact_stiffness_mpa_mmNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.7
    • addedInput schema / properties / workspace
      Added value: +{
      +  "default": "",
      +  "description": "Run this call in this named workspace",
      +  "title": "Workspace",
      +  "type": "string"
      +}
  2. Addedv0.5.6

TDQS

A4.6/5.0
Behavior5/5

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

Goes far beyond the annotations: async job semantics (poll job_result), a degradation dict when ccx is absent, the explicit failure condition (fall not arrested or energy growth), ~20 % banding on real parts, and measured contact-model pathologies (face-to-face falls through a corner strike, node-to-face locks up on flat landings) that explain the 'auto' default. It also discloses scope limits — no friction, failure or erosion — which an agent cannot infer from readOnlyHint/destructiveHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and async contract before descending into parameter and accuracy detail, and nearly every sentence adds technical content. The ~40-field return enumeration is dense and slightly unwieldy, but it substitutes for the absent output schema, so it earns its space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 23-parameter, no-output-schema physics solver, the definition covers the workflow (submit → poll job_result), solver/model selection, accuracy expectations, and the gate fields an agent must interpret. The only real holes are the handful of unmentioned parameters, which are minor relative to the overall coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 4 %, so the description carries nearly the whole burden and mostly succeeds: it explains the exactly-one-of `velocity_m_s`/`drop_height_mm`, the free-form 3-vector meaning of `direction` (corner drop turns the floor, not the mesh), the material requirements with no defaults and the √(E·ρ) scaling, the `yield_mpa`/`plastic`+`tangent_mpa` criterion arms, `time_step_s` fixed-step tradeoffs, and `duration_s`/`samples` defaults. Several parameters remain unexplained — `gap_mm`, `gravity`, `char_length_mm`, `max_time_step_s`, `contact_stiffness_mpa_mm`, `workspace` — which keeps it from a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Transient DROP / IMPACT dynamics'), the physical setup (mesh flies into a rigid floor via penalty contact, integrated with CalculiX *DYNAMIC), and its position in the sibling graph as the solve that `drop_impact` escalates to. There is no ambiguity about what this call does versus any neighbor.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear routing context ('the solve `drop_impact` escalates to') plus explicit decision rules for `method` (implicit for ms-scale drops, explicit for stress-wave events ≲100 µs) and `contact` ('auto' by measurement). It stops short of stating when to avoid this tool entirely versus analytic siblings such as `bar_impact`, which is only referenced as a validation target.

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

Deploy Server

Other Tools