# resolve_assembly_from_description

Resolve a plain-English job description to candidate catalogue assemblies and the fields you'll need to compute one. Deterministic router — it does NOT return a Bill of Quantities and NEVER guesses parameter values; it returns candidate slugs (plural when ambiguous, with clarifying questions), each assembly's tier, whether it supports compute_multi_section_assembly, and per-field metadata (unit, min/max, default). Then call compute_<slug> (or compute_multi_section_assembly) with the values you fill in. Also known as compute_from_description. Example: {"description":"a 3 m deep manhole","preferred_standard":"MMHW"}.

Agent View of the PolicyLayer registry record for `resolve_assembly_from_description`. HTML page: https://policylayer.com/tools/com-civilquants-civilquants/resolve-assembly-from-description

## Facts

- Tool: `resolve_assembly_from_description`
- Server: Civilquants (`https://api.civilquants.com/mcp`) — https://policylayer.com/tools/com-civilquants-civilquants.md
- Homepage: https://github.com/https://api.civilquants.com/mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 3 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `description` | string | yes |  |
| `preferred_standard` | object | no |  |
| `return_resolution_log` | boolean | no |  |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "resolve_assembly_from_description",
    "arguments": {
      "description": "<description>"
    }
  }
}
```

## Why resolve_assembly_from_description is rated Low

The tool purely resolves/queries a catalogue based on a plain-English description and returns metadata (candidate slugs, field definitions, clarifying questions). It has no side effects, does not execute computations, and explicitly states it does not return a Bill of Quantities or guess values. This is a read/lookup operation with low blast radius.

From the tool's own definition: "Deterministic router — it does NOT return a Bill of Quantities and NEVER guesses parameter values; it returns candidate slugs... and per-field metadata"

## Use case

AI agents call resolve_assembly_from_description to retrieve information from Civilquants without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Civilquants:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "resolve_assembly_from_description": {}
  }
}
```

## Other tools on Civilquants (55)

- `compute_box_culvert` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-box-culvert.md
- `compute_combined_services_trench` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-combined-services-trench.md
- `compute_connection_to_existing` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-connection-to-existing.md
- `compute_ditch` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-ditch.md
- `compute_embankment_cross_section` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-embankment-cross-section.md
- `compute_end_area_earthworks` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-end-area-earthworks.md
- `compute_gabion_wall` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-gabion-wall.md
- `compute_headwall_attenuation_outlet` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-headwall-attenuation-outlet.md
- `compute_highway_drainage_channel` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-highway-drainage-channel.md
- `compute_lighting_column` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-lighting-column.md
- `compute_multi_section_assembly` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-multi-section-assembly.md
- `compute_pad_foundation` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-pad-foundation.md
- `compute_parapet` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-parapet.md
- `compute_pipe_bedding` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-pipe-bedding.md
- `compute_reinforced_soil_wall` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-reinforced-soil-wall.md
- `compute_road_marking` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-road-marking.md
- `compute_single_service_run` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-single-service-run.md
- `compute_soakaway` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-soakaway.md
- `compute_soil_nailed_slope` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-soil-nailed-slope.md
- `compute_traffic_sign` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-traffic-sign.md
- `compute_utility_chamber` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-utility-chamber.md
- `compute_utility_kiosk_base` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/compute-utility-kiosk-base.md
- `recompute_project` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/recompute-project.md
- `render_skill_report` — Execute — https://policylayer.com/tools/com-civilquants-civilquants/render-skill-report.md
- `compute_attenuation_tank` — Read — https://policylayer.com/tools/com-civilquants-civilquants/compute-attenuation-tank.md
- `compute_bored_pile_wall` — Read — https://policylayer.com/tools/com-civilquants-civilquants/compute-bored-pile-wall.md
- `compute_cantilever_wall` — Read — https://policylayer.com/tools/com-civilquants-civilquants/compute-cantilever-wall.md
- `compute_carrier_pipe_run` — Read — https://policylayer.com/tools/com-civilquants-civilquants/compute-carrier-pipe-run.md
- `compute_catchpit` — Read — https://policylayer.com/tools/com-civilquants-civilquants/compute-catchpit.md
- `compute_edge_drain` — Read — https://policylayer.com/tools/com-civilquants-civilquants/compute-edge-drain.md
- …and 25 more: https://policylayer.com/tools/com-civilquants-civilquants.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-civilquants-civilquants · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-civilquants-civilquants