Databricks Field Guide by TechFabric

Explore a Databricks concept

explore_concept

Read-onlyIdempotent

Interactive: explains one Databricks concept step by step from the Field Guide's chapters: delta-transaction-log, liquid-clustering-vs-zorder, spark-shuffle-and-stages, unity-catalog-privilege-inheritance, photon-vs-classic-cost, cluster-autoscaling, streaming-watermarks, medallion-layers, lakebase-branching, serverless-vs-classic, mlflow-model-lifecycle. Call it first when the user asks "how does the Delta transaction log work?", "show me watermarks step by step" or "visualise Unity Catalog privilege inheritance", rather than answering from memory or running code. Every point comes with the guide's own sentence and its section URL; the result also carries a worked example and the data an interactive model draws (a Delta log to step through, files skipped under each layout, Spark stages and skew, Unity Catalog grants on a tree, cost curves from the guide's rates, a warehouse's day, a watermark timeline, and more), with what the model assumes said apart from what the guide states. In a host that renders MCP Apps it opens as an interactive view; the text is complete without it. Unknown or no concept: the list (with form: true, a terminal that shows forms asks which).

Input Schema

Name	Required	Description
`done`	No	With exam: the plan steps done so far, by number or id
`exam`	No	Opened from an exam_prep plan: the exam's id, so the card says which step this is and its Next returns to the plan
`form`	No	true: with no concept (or one that isn't there), in a client that shows forms and no MCP Apps view, ask the reader which concept to step through. Left out, the result is the list.
`step`	No	With exam: the plan step this card was opened from (its id, as the plan's call gives it)
`concept`	No	The concept: delta-transaction-log, liquid-clustering-vs-zorder, spark-shuffle-and-stages, unity-catalog-privilege-inheritance, photon-vs-classic-cost, cluster-autoscaling, streaming-watermarks, medallion-layers, lakebase-branching, serverless-vs-classic, mlflow-model-lifecycle. A plain name works too ("watermarks", "z-order", "photon"). Omit it, or name one that isn't there, for the list.

Output Schema

Name	Required	Description
`sim`	Yes	The data the interactive view animates; its numbers are a model, said under assumptions, except the rates, which are the guide's
`try`	Yes
`asked`	Yes
`build`	Yes	The commit of the deploy that answered
`guide`	No	Guided mode for the view: steps, each a short title, one of the guide's points as its body, an optional tip, an illustrative scene and the section it cites; then a recap
`title`	Yes
`ttlMs`	Yes	How long this answer may be kept before asking again, in milliseconds
`chapter`	Yes
`concept`	Yes	The concept's id; null when none matched (see available)
`related`	Yes
`summary`	Yes
`sections`	Yes
`withheld`	Yes
`available`	Yes
`plan_step`	No	Opened from an exam plan: this step's place (n of total), the steps done with this one, the plan's next step, and back, the call that returns to the plan
`what_next`	No	What to do after this concept, as calls: from a plan, its next step and back to it; a quiz on it; the next concept
`assumptions`	Yes
`explanation`	Yes
`index_built`	Yes	When this deploy's index was built (ISO 8601)

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 28, 2026

addedInput schema / properties / done

Added value: +{
+  "description": "With exam: the plan steps done so far, by number or id",
+  "items": {
+    "anyOf": [
+      {
+        "maxLength": 200,
+        "type": "string"
+      },
+      {
+        "type": "integer"
+      }
+    ]
+  },
+  "maxItems": 60,
+  "type": "array"
+}

addedInput schema / properties / exam

Added value: +{
+  "description": "Opened from an exam_prep plan: the exam's id, so the card says which step this is and its Next returns to the plan",
+  "maxLength": 120,
+  "type": "string"
+}

addedInput schema / properties / step

Added value: +{
+  "description": "With exam: the plan step this card was opened from (its id, as the plan's call gives it)",
+  "maxLength": 200,
+  "type": "string"
+}

addedOutput schema / properties / plan_step

Added value: +{
+  "description": "Opened from an exam plan: this step's place (n of total), the steps done with this one, the plan's next step, and back, the call that returns to the plan",
+  "type": [
+    "object",
+    "null"
+  ]
+}

addedOutput schema / properties / what_next

Added value: +{
+  "description": "What to do after this concept, as calls: from a plan, its next step and back to it; a quiz on it; the next concept",
+  "items": {
+    "properties": {
+      "call": {
+        "type": "object"
+      },
+      "id": {
+        "type": "string"
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "label",
+      "call"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed1 schema field changedOct 27, 2026

addedInput schema / properties / form

Added value: +{
+  "description": "true: with no concept (or one that isn't there), in a client that shows forms and no MCP Apps view, ask the reader which concept to step through. Left out, the result is the list.",
+  "type": "boolean"
+}

Changed1 schema field changedOct 24, 2026

addedOutput schema / properties / guide

Added value: +{
+  "description": "Guided mode for the view: steps, each a short title, one of the guide's points as its body, an optional tip, an illustrative scene and the section it cites; then a recap",
+  "properties": {
+    "callouts": {
+      "items": {
+        "properties": {
+          "label": {
+            "type": "string"
+          },
+          "n": {
+            "type": "string"
+          },
+          "step": {
+            "type": "integer"
+          },
+          "x": {
+            "type": "number"
+          },
+          "y": {
+            "type": "number"
+          }
+        },
+        "required": [
+          "n",
+          "x",
+          "y",
+          "step",
+          "label"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "caption": {
+      "description": "Says the pictures are illustrative",
+      "type": "string"
+    },
+    "level": {
+      "type": "string"
+    },
+    "recap": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "steps": {
+      "items": {
+        "properties": {
+          "body": {
+            "type": "string"
+          },
+          "cite": {
+            "properties": {
+              "section": {
+                "type": "string"
+              },
+              "url": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "url",
+              "section"
+            ],
+            "type": "object"
+          },
+          "id": {
+            "type": "string"
+          },
+          "scene": {
+            "type": "object"
+          },
+          "tip": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "title",
+          "body",
+          "tip",
+          "scene",
+          "cite"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "views": {
+      "items": {
+        "type": "string"
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "level",
+    "caption",
+    "views",
+    "callouts",
+    "steps",
+    "recap"
+  ],
+  "type": [
+    "object",
+    "null"
+  ]
+}

AddedOct 23, 2026

TDQS

A4.1/5.0

Behavior5/5

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

The description adds substantial behavioral detail beyond the annotations: every point includes the guide's own sentence and section URL, results carry a worked example and interactive-model data, assumptions are separated from guide statements, and MCP Apps rendering is described. It also explains what happens when no concept is provided or the concept is unknown.

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 and triggering guidance are front-loaded, and most clauses carry useful information for a tool with multiple modes. However, the single dense paragraph is long and repeats the concept list that also appears in the schema, making it less scannable than it could be.

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 annotations, full schema coverage, and output schema, the description is complete: it covers purpose, when to call, output shape, interactive rendering, concept fallback, and the separation of guide facts from model assumptions. An agent has enough context to invoke it correctly without opening the schema.

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 documents all five optional parameters, including concept, form, exam, step, and done. The description reinforces concept naming and the no-concept list behavior, but does not add much beyond the 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 states a specific verb and resource: it explains one Databricks concept step by step from the Field Guide's chapters, with a concrete list of supported concepts. It distinguishes the tool from answering from memory or running code, but does not explicitly differentiate it from sibling tools such as explore_diagram or get_chapter.

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 gives clear triggering guidance: call it first when the user asks conceptual how-to questions like how the Delta transaction log works or to show watermarks step by step. It also states the fallback for unknown or missing concepts, though it does not name sibling tools as alternatives.

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

All Databricks Field Guide by TechFabric 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.