mcp-fabric-api

kql_database_update_definition

Update a KQL database definition by providing definition parts inline or a directory path. Use to modify database schema or settings through Fabric API.

Instructions

Update a KQL database's definition (long-running). Accepts definition parts inline or a directory path.

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": {
      "workspaceId": "<workspaceId>",
      "kqlDatabaseId": "<kqlDatabaseId>"
    },
    "name": "kql_database_update_definition"
  }
}

Input Schema

Name	Required	Description
`parts`	No	Array of definition parts to upload
`workspaceId`	Yes	The workspace ID
`kqlDatabaseId`	Yes	The KQL database ID
`partsDirectoryPath`	No	Path to a directory containing definition files

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.8.0Sep 6, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already indicate this is a write operation and not read-only, so the description's main behavioral addition is 'long-running,' which is useful. However, it does not explain what the long-running behavior means for the caller, such as whether it returns an operation ID, how to poll for completion, or whether the update is atomic or incremental.

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 two short sentences with no filler. It front-loads the core operation and long-running nature, then immediately covers the two input modes. Every word contributes useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the minimal annotations and lack of an output schema, the description adequately covers what the operation does and the main input options, but it is incomplete about operation outcomes and tracking. An agent still has to infer what a successful or in-progress update returns and how to handle the long-running aspect.

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 100%, so the baseline is 3. The description adds value by clarifying that 'parts' and 'partsDirectoryPath' are alternative input modes: definition parts can be supplied inline or via a directory path. This relationship is not explicit in the schema itself.

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 states a specific action and resource: it updates a KQL database's definition, which clearly separates it from general kql_database_update. The parenthetical 'long-running' adds an important distinguishing trait, and the mention of inline parts versus directory path is non-tautological and concrete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies it should be used for full-definition updates rather than simple database property changes, but it never explicitly names alternatives like kql_database_update or says when not to use it. The 'long-running' note gives some situational guidance, but no exclusion or sibling routing is provided.

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

Deploy Server