Skip to main content
Glama
HorizunGroup

Horizun PBI MCP

Official
by HorizunGroup

pbi_validate_tmdl

Read-only

Validates TMDL models for errors that block opening in Power BI Desktop. Runs static linting and, optionally, a deeper parse using Power BI's own serializer.

Instructions

Comprueba si un modelo TMDL abrira, sin abrir Power BI Desktop.

Dos capas. Un lint estatico que caza las trampas que solo se veian al abrir (una propiedad de tabla colocada despues de sus hijos, un comentario '///' sobre una relacion, una medida que se llama como una columna de su tabla, medidas duplicadas, referencias rotas) y, si estan las DLL, un parseo con el MISMO serializador que usa Power BI.

Cada hallazgo trae rule, severity, el archivo y la linea. Si el parseo no se pudo ejecutar se dice (parse_checked: false) en vez de darlo por bueno.

Hay fallos que NINGUN analisis estatico ve porque dependen de los datos —un blanco en el lado 'uno' de una relacion, un separador decimal mal interpretado—. Salen en limitations: para esos hay que refrescar.

path: carpeta definition del modelo, la carpeta .SemanticModel o el .pbip. Si se omite, el proyecto activo. use_tom=False: solo el lint estatico, sin tocar las DLL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNo
use_tomNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Annotations already declare readOnlyHint=true, but the description adds substantial behavioral detail: two validation layers (static lint and parser using the same serializer as Power BI), the exact shape of findings (rule, severity, file, line), the parse_checked=false edge case, and a list of data-dependent failures that the tool cannot catch. This goes far beyond the annotation and gives the agent an accurate model of what to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact yet information-dense. It front-loads the purpose, then systematically covers the two validation layers, output structure, limitations, and parameters. Every sentence contributes unique value, and the paragraph breaks guide the reader through the key concepts without unnecessary verbosity.

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?

Given the tool's complexity (two-layer validation with multiple edge cases) and the existence of an output schema, the description covers all needed aspects: what the tool does, how results are structured, what it cannot detect, and parameter semantics. Limitations are explicitly documented, and the presence of an output schema means return values need not be spelled out in detail.

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

Parameters5/5

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

The input schema has only minimal titles and defaults, with 0% schema description coverage. The description fully compensates by explaining that 'path' accepts a definition folder, a .SemanticModel folder, or a .pbip, and defaults to the active project, and that 'use_tom=False' runs only the static lint without touching DLLs. Both parameters are given clear, actionable semantics.

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?

The description opens with a specific verb and resource: 'Comprueba si un modelo TMDL abrira, sin abrir Power BI Desktop' (Checks if a TMDL model will open, without opening Power BI Desktop). It distinguishes this tool from siblings by focusing on TMDL model validation and explicitly noting the no-Desktop requirement, making the purpose unmistakable.

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?

The description provides clear context for use: validating TMDL models without opening Desktop, with path options (definition folder, .SemanticModel, .pbip) and a fallback to the active project. It describes the two-layer validation and limitations, but does not explicitly name alternative tools or state when not to use this tool, so it stops short of full exclusion guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HorizunGroup/horizun-pbi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server