Skip to main content
Glama

Setup Status

setup_status
Read-only

Diagnose AnkusDrive setup by resolving FreeCAD and every solver family, then report found/missing items with exact per-platform fix commands. Read-only and side-effect free.

Instructions

The machine-readable form of ankusdrive doctor — resolve FreeCAD and every solver family and report, per item, found/missing with the exact fix. Call this when the user asks to set up, diagnose, or finish installing AnkusDrive, then walk them through the per-item fix/install_hint commands for their platform.

Read-only and side-effect-free: nothing is executed or installed and no environment is mutated (verify_freecad_boot=True additionally boots FreeCAD once, time-boxed, purely to read back its version — leave it False unless the user doubts the install actually runs).

verify_image=True additionally checks, OVER THE NETWORK, that the solver container's image was signed by this repository — use it when the user asks whether the solvers they are running are authentic. It adds container_image.verification = {status, reason, repo, workflow, allowed_by_config, self_declared}, where status is: • verified — provenance names this repository's image workflow; • unsigned — no attestation: an image the user built themselves (common and legitimate), one published before signing existed, or no network/gh. Relay it as expected-for-a-custom-image, and mention ANKUSDRIVE_ALLOW_UNVERIFIED_IMAGE=1 silences it; • mismatch — an attestation exists but names a DIFFERENT repository. Say so plainly: that is an image claiming to be ours. No setting silences it; • unavailable — the check could not run (reason says why). Never report this as authentic. self_declared is what the image says about itself and is never evidence — only the signature is.

Returns {platform: {system, machine}, freecad: {available, path, source, version?, fix?}, install: {kind, source} (venv | pipx | uv_tool | uvx | mcpb — the install every fix string is written for), toolsets: {enabled, disabled: {family: {label, tools, enable}}} (tool families switched off in this install and exactly how to switch each on), run_script: {allowed, enable?} (whether the run_script tool may execute agent-written code here), solvers: {available, unwired, prepared_case_only, solvers: {name: {..., install_hint | wire_hint}}, families: {family: {solvers, available, unwired, prepared_case_only, any_available}}, extras}} — families[*].any_available is what gates each *_submit family, and every unavailable item carries its own fix string. A solver under prepared_case_only resolves but no AnkusDrive tool can build it a case, so it does not make its family available (SU2/cfd — issue #237).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "setup_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
workspaceNoRun this call in this named workspace
verify_imageNo
verify_freecad_bootNo

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. Changed1 schema field changedv0.5.6
    • addedInput schema / properties / verify_image
      Added value: +{
      +  "default": false,
      +  "title": "Verify Image",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: nothing is executed, installed, or mutated; `verify_freecad_boot` invisibly boots FreeCAD once (time-boxed); `verify_image` performs a network call. It also tells the agent how to interpret and relay each verification status, including that `self_declared` is never evidence. Minor tension worth noting: `openWorldHint=false` while the opt-in `verify_image` path does network I/O, though the description itself discloses that network access in caps rather than hiding it.

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 one-line purpose, then the usage trigger, then safety, then flags, then return shape — a sensible order with bullet/code formatting that aids scanning. It is long for a zero-required-parameter tool, and the exhaustive return-shape recitation is dense, but since no output schema exists most of it earns its place.

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

Completeness4/5

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

With no output schema, the description carries the full return contract and does so thoroughly (`platform`, `freecad`, `install.kind`, `toolsets`, `run_script`, `solvers`, `families[*].any_available`). The `prepared_case_only` / issue #237 note explains a non-obvious availability rule. Only real omission is how the `workspace` parameter changes what is diagnosed, and error behavior.

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 description coverage is only 33% (only `workspace` is documented in the schema), so the description must compensate, and it does for `verify_image` and `verify_freecad_boot` — explaining defaults, cost, and the exact diagnostic question each answers. The remaining gap is `workspace`, which the description never mentions, so the agent cannot tell how workspace scoping affects a setup diagnosis.

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?

Names a specific resource and action: the machine-readable form of `ankusdrive doctor` that resolves FreeCAD and every solver family and reports per-item found/missing with an exact fix. It is clearly distinguishable from every sibling in the list (ping, version, render_capabilities, solve_capabilities) because it is explicitly a per-item environment resolution report, not a capability listing.

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

Usage Guidelines5/5

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

Gives an explicit trigger ('when the user asks to set up, diagnose, or finish installing AnkusDrive') plus a follow-on directive (walk them through the per-item `fix`/`install_hint` commands for their `platform`). It also gives when-not guidance for each optional flag: 'leave it False unless the user doubts the install actually runs' and 'use it when the user asks whether the solvers they are running are authentic'.

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