Databricks Field Guide by TechFabric

Decide with the guide

decide

Read-onlyIdempotent

Interactive: walks a Databricks decision one question at a time (which-compute, serverless-or-classic, lakebase-or-delta, genie-or-dashboard, streaming-or-batch): every answer rests on the guide's own sentences, verbatim, with the section to read. Call it when the user asks "should I use serverless or classic", "Lakebase or Delta?", "Genie or a dashboard?" or "which compute for this job". The text gives the whole tree; send choices (option numbers so far) for the answer. In a terminal that shows forms, form: true asks each question as a form.

Input Schema

Name	Required	Description
`form`	No	true: in a client that shows forms (elicitation) and no MCP Apps view, ask the reader each question of the decision as a form and return the result. Send it only when the reader wants to answer in forms; left out, the result is unanswered.
`choices`	No	The reader's choices so far, as option numbers from the first question: the result then carries where they are, or the answer
`question`	No	The decision, in plain words or by id: which-compute, serverless-or-classic, lakebase-or-delta, genie-or-dashboard, streaming-or-batch. Omit it for the list.

Output Schema

Name	Required	Description
`tree`	Yes
`walk`	Yes
`asked`	Yes
`build`	Yes	The commit of the deploy that answered
`nodes`	Yes
`start`	Yes
`title`	Yes
`ttlMs`	Yes	How long this answer may be kept before asking again, in milliseconds
`result`	Yes	The answer reached, when the choices reach one
`current`	No
`withheld`	Yes
`available`	Yes
`index_built`	Yes	When this deploy's index was built (ISO 8601)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 27, 2026

addedInput schema / properties / form

Added value: +{
+  "description": "true: in a client that shows forms (elicitation) and no MCP Apps view, ask the reader each question of the decision as a form and return the result. Send it only when the reader wants to answer in forms; left out, the result is unanswered.",
+  "type": "boolean"
+}

AddedOct 24, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds the interaction model the annotations can't: one question per call, options passed as numbers-so-far to advance state, and a form:true variant for elicitation-capable terminals. It does not say what happens with invalid or out-of-range choices, which is a minor gap.

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

Conciseness3/5

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

The core purpose is front-loaded, but the prose is overstuffed: the five decision ids appear in the first sentence and the same intent is re-expressed as three example questions, and the form:true sentence repeats the schema description almost verbatim. The long parenthetical and multi-clause sentences make it slower to parse than needed.

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?

With an output schema present and rich annotations, the description supplies what remains: the ask-answer loop, the decision-id vocabulary, and the interactive form variant. Only edge behavior (invalid choice numbers, exceeding maxItems) is left unstated.

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 baseline is 3; the description still adds meaning by framing 'choices' as option numbers accumulated from the first question rather than a fresh set, and by clarifying that omitting 'question' yields the list. The form flag's purpose is restated with the terminal condition, though it largely duplicates the schema text.

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 resource ('walks a Databricks decision one question at a time') and enumerates the five decision trees it covers (which-compute, serverless-or-classic, lakebase-or-delta, genie-or-dashboard, streaming-or-batch). The 'every answer rests on the guide's own sentences, verbatim, with the section to read' clause distinguishes it from exploratory siblings like search_guide or explore_concept.

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?

Gives concrete invocation triggers as quoted user phrasings ('should I use serverless or classic', 'Lakebase or Delta?', 'which compute for this job'), which is strong positive guidance. It also notes 'Omit it for the list' for the question param. It does not name a competing sibling or state when NOT to use it, so it falls short of a full when/when-not/alternatives statement.

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.