Krusgraph

Draft a Power BI semantic model (TMDL, nothing created)

semantic_model_draft

Read-only

Drafts the plan as a Power BI semantic model in TMDL (Direct Lake on the source's SQL analytics endpoint): relationships with cardinality and filter direction, one active path per table pair, suggested measures that sum at the right level (validate=true also counts header amounts repeated in a flat table). Requires workspace and source. Returns JSON {path: content} for the definition folder plus README.generated.md listing the decisions to check. Changes nothing; create_semantic_model creates the item, compare_semantic_model checks an existing model. Errors: {error, kind, hint}.

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>",
      "source": "<source>"
    },
    "name": "semantic_model_draft"
  }
}

Input Schema

Name	Required	Description	Default
`keys`	No	Primary keys replacing the inferred ones. Default: inferred. Example: {"order_items": ["order_id", "line_no"]}.
`name`	No	Name of the semantic model in the draft. Default "semantic_model". Example: "shop_model".	semantic_model
`schema`	No	Schema in the source. Default "dbo".	dbo
`source`	Yes	Lakehouse, warehouse or SQL database, name or id.
`tables`	No	Table names or globs to show. Default all. Example: ["sales_*"].
`validate`	No	true runs validate_plan's counting queries and includes the counts; false (default) reads metadata only.
`confirmed`	No	Relationships the user confirmed, added to the plan. Default none. Example: [{"source": "orders", "source_cols": ["ship_to_id"], "target": "addresses", "target_cols": ["address_id"]}].
`workspace`	Yes	Fabric workspace, name or id.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

addedInput schema / properties / validate

Added value: +{
+  "default": false,
+  "description": "true runs validate_plan's counting queries and includes the counts; false (default) reads metadata only.",
+  "title": "Validate",
+  "type": "boolean"
+}

Changed7 schema fields changedOct 29, 2026

addedInput schema / properties / confirmed / description

Added value: +"Relationships the user confirmed, added to the plan. Default none. Example: [{\"source\": \"orders\", \"source_cols\": [\"ship_to_id\"], \"target\": \"addresses\", \"target_cols\": [\"address_id\"]}]."

addedInput schema / properties / keys / description

Added value: +"Primary keys replacing the inferred ones. Default: inferred. Example: {\"order_items\": [\"order_id\", \"line_no\"]}."

addedInput schema / properties / name / description

Added value: +"Name of the semantic model in the draft. Default \"semantic_model\". Example: \"shop_model\"."

addedInput schema / properties / schema / description

Added value: +"Schema in the source. Default \"dbo\"."

addedInput schema / properties / source / description

Added value: +"Lakehouse, warehouse or SQL database, name or id."

addedInput schema / properties / tables / description

Added value: +"Table names or globs to show. Default all. Example: [\"sales_*\"]."

addedInput schema / properties / workspace / description
```
Added value: +"Fabric workspace, name or id."
```

First observedOct 27, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description still adds real value by confirming nothing is created, specifying the return shape {path: content} plus a README.generated.md of decisions to check, and documenting the error envelope {error, kind, hint}. The only gap is that it doesn't describe how large the generated file set can get or any limits on table/relationship volume.

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-loads the action and the TMDL/Direct Lake framing, then packs what is generated, requirements, return shape, sibling disambiguation and error format into a few lines with no filler. It is dense to the point of being parenthetical-heavy, which costs a point on readability but not on usefulness.

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 an 8-parameter draft generator with an output schema, the definition covers the non-obvious essentials: the storage mode, the modeling constraints applied (one active path per table pair), the fact that nothing is persisted, the artifact set produced, and the error contract. An agent can call this correctly and interpret the result without further context.

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 description coverage is 100%, so the schema already explains keys, name, schema, source, tables, confirmed and validate. The description adds one genuinely new nuance — validate=true also counts header amounts repeated in a flat table — but otherwise restates schema content (confirmed relationships being "added to the plan" is already in the schema text). Baseline 3 plus a small increment is appropriate.

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 artifact: "Drafts the plan as a Power BI semantic model in TMDL (Direct Lake on the source's SQL analytics endpoint)". It goes further and enumerates what the draft contains (relationships with cardinality and filter direction, one active path per table pair, suggested measures), which separates it cleanly from create_semantic_model and compare_semantic_model.

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?

Explicitly bounds the tool with "Changes nothing" and names both alternatives with their distinct roles: "create_semantic_model creates the item, compare_semantic_model checks an existing model". It also states the required inputs ("Requires workspace and source"), so an agent knows both when to pick this tool and what it must supply.

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

All Krusgraph 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.