Aevia

Import openLCA project

lca_import_project

Import an openLCA project: assess each variant and save one comparison. project is the project's name as engine_search(kind='project') lists it, or a unique part of it, in the database named by engine, else this connection's default, which must be writable. Each enabled variant's product system is imported into workspace as an s<N> (one already there is refreshed) and assessed once as an a<N> with the variant's amount, unit and allocation and the project's method and normalization/weighting set; the variants are saved as one comparison c<N>, returned as primary_ref. openLCA's API cannot calculate a project; this reproduces it variant by variant, each at its own amount (functional equivalence is not checked). Without confirm: true the call returns a preview and starts nothing. A run within 45 seconds returns its result; a longer one returns a task_id for lca_get_task_status. Refused: fewer than 2 or more than 9 enabled variants, or parameter redefinitions. Disabled variants are skipped.

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": {
      "workspace": "<workspace>",
      "project": "<project>"
    },
    "name": "lca_import_project"
  }
}

Input Schema

Name	Required	Description
`engine`	No	Name of the engine database, as `lca_get(kind='engines')` lists it (case-insensitive). Omitted: this connection's default engine.
`confirm`	No	Run the import: the systems, one assessment per variant and the comparison. Without it the call returns a preview of what would be imported and starts nothing.
`project`	Yes	The openLCA project's name as `engine_search(kind='project')` lists it (backticks optional), or a unique part of it.
`workspace`	Yes	Name of the workspace to work in, as `lca_get(kind='workspaces')` lists it (backticks optional). Named on every call: several conversations can share one connection, and each names its own workspace. The connection's default is often an empty sandbox rather than the user's work.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations, it discloses exactly what is created (`s<N>` product systems, one `a<N>` assessment per variant with specific amount/unit/allocation/method settings, and a `c<N>` comparison returned as `primary_ref`), that a pre-existing `s<N>` is refreshed, that long runs return a `task_id`, and which configurations are refused. This is unusually complete behavioral context for a mutating tool that is neither idempotent nor destructive by annotation.

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?

The purpose is front-loaded and the rest is dense but mostly load-bearing (variant limits, preview gate, 45-second cutoff). Some clauses duplicate schema text, notably the restatement of how `project` and `workspace` names are listed, costing a little tightness in an otherwise efficient block.

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?

With no output schema, the description still covers the return shape (either the result or a `task_id`, plus `primary_ref`), the side effects, the failure modes, and the calculational caveat that functional equivalence is not checked. Nothing an agent needs in order to call it correctly or interpret the response is missing.

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 already 100%, yet the description adds real meaning: `project` resolves as a full name or unique substring in the database named by `engine`, falling back to the connection default, which must be writable. `workspace` and `confirm` behavior are also restated in operational terms rather than merely echoing the schema.

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?

"Import an openLCA project: assess each variant and save one comparison" gives a specific verb, resource, and outcome, and the detailed body makes clear this is a whole-project import rather than the sibling lca_import_system's single-system import. An agent can distinguish the two without opening either schema.

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?

It states the preconditions (project must resolve in a writable database, 2-9 enabled variants, no parameter redefinitions), the dry-run gate (no `confirm: true` = preview only), and routes the agent to engine_search and lca_get_task_status where relevant. It never explicitly says when to prefer this over lca_import_system or lca_compose_linked for narrower cases, so the choice among siblings is only implied.

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

All Aevia tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?