Databricks Field Guide by TechFabric

Review Databricks code

review_databricks_code

Read-onlyIdempotent

Check one file of SQL, Python (PySpark, a notebook's source) or YAML (a Databricks Asset Bundle, job, cluster or warehouse config) against the Field Guide's own best-practice rules, deterministically: partitioning where the guide would cluster, secrets and storage paths written into code, grants to people rather than groups, environments in table names, jobs on all-purpose clusters or without timeouts, warehouses and clusters without auto-stop, bundle targets without their modes, and the rest of the rules the chapters state. Each finding gives the line, why, the fix, the guide's passage verbatim with its section URL, and the docs.databricks.com links the guide cites for it; the result also lists the sections worth reading for this code. No model is called: weigh the findings yourself. One file per call.

Input Schema

Name	Required	Description
`code`	Yes	The file's contents: SQL, Python (PySpark, a notebook's source) or YAML (a Databricks Asset Bundle, job, cluster or warehouse config). At most 48000 characters; review a larger file in parts.
`lang`	No	sql, python or yaml. Omit to detect it from the filename or the code.
`filename`	No	The file's path in the repository, e.g. resources/nightly.job.yml: used to detect the language and echoed back

Output Schema

Name	Required	Description
`lang`	Yes
`note`	Yes
`build`	Yes	The commit of the deploy that answered
`lines`	Yes
`total`	Yes
`ttlMs`	Yes	How long this answer may be kept before asking again, in milliseconds
`filename`	Yes
`findings`	Yes
`sections`	Yes
`withheld`	Yes
`index_built`	Yes	When this deploy's index was built (ISO 8601)
`rules_checked`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations: discloses determinism, that no model is invoked, the exact shape of each finding (line, why, fix, verbatim guide passage with section URL, docs links), and that sections worth reading are also returned. The one-file-per-call constraint is a real behavioral limit an agent must plan around.

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-loaded with the verb, the input types and the deterministic standard, then the output shape. The long enumeration of rule categories is informative but borders on a run-on sentence; it earns most of its length but could be tightened.

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 a 3-parameter, fully-described, read-only tool with an output schema, this covers everything an agent needs: what it accepts, what it returns, that it is deterministic, and the one-file scope. Nothing material is left to inference.

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 meaning by spelling out what counts as 'code' (SQL, PySpark or notebook source, DAB/job/cluster/warehouse YAML), which clarifies the accepted inputs beyond the terse schema text. It does not repeat the 48000-character limit or lang-omit behavior, which stay in the schema.

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 ('Check one file of SQL, Python ... or YAML') and the exact standard applied ('the Field Guide's own best-practice rules, deterministically'). It enumerates the concrete classes of violations, so an agent can tell it apart from siblings like search_guide or get_chapter without opening any schema.

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?

'One file per call' and 'No model is called: weigh the findings yourself' give clear operating context and a post-processing instruction. It does not explicitly name a sibling alternative or an exclusion (e.g. when to prefer search_guide for prose lookup), so it stops short of full routing guidance.

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.