Skip to main content
Glama
semlayer MCP server

semlayer MCP server

export_layer

DestructiveIdempotent

Write a snapshot of the semantic layer in another tool's format, such as dbt, to a chosen path. The export is lossy and not kept in sync with the layer.

Instructions

Write a snapshot of the layer in another tool's format.

    path: where the user wants it written.
    target: `dbt` today. On request only, and lossy -- the result says
    what the format could not carry. Nothing keeps it in step with the
    layer afterwards and you must keep answering from the layer, never
    from the export.
    

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": {
      "target": "<target>",
      "path": "<path>"
    },
    "name": "export_layer"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesWhere to write the export, as the user chose it.
targetYesThe format to write. `dbt` is the only one today.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • addedInput schema / properties / path / description
      Added value: +"Where to write the export, as the user chose it."
    • addedInput schema / properties / target / description
      Added value: +"The format to write. `dbt` is the only one today."
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and readOnlyHint=false; the description goes beyond them by disclosing that the export is lossy, that the result reports what could not be carried, and that the export is not kept in sync afterwards. The one notable omission is overwrite behavior for an existing file at path, which is exactly what the destructive hint implies.

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 core action and the strongest caveat (lossy, no ongoing sync) are front-loaded in the first sentence, and the rest is terse. The indented per-parameter lines repeat schema text and could be trimmed without losing information.

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?

Because an output schema exists, the description needn't enumerate return values, and it usefully points at what the result contains. It covers when to use, the lossiness caveat, and the staleness warning; the remaining gap is what happens to an existing file at path.

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

Parameters3/5

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

Schema coverage is 100% and the schema already says path is 'as the user chose it' and target is the format to write, so the description's path/target glosses are largely duplicative. The only added nuance is reinforcing that the path comes from the user rather than the agent, which is marginal against a fully documented schema.

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

Purpose4/5

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

The description gives a specific verb and resource — write a snapshot of the layer into another tool's format — and names the only supported format (dbt). It is clearly distinct from save_layer/load_layer by framing this as a one-way export to a foreign format, though it never explicitly contrasts with those siblings.

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 a real gating condition ('On request only'), which tells the agent not to invoke it proactively, and adds a post-call rule ('keep answering from the layer, never from the export'). It stops short of naming the alternative for persistence needs, which would have earned a 5.

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