Name: add-tools
Rating: 67.2 (1 reviews)
Author: databricks

add-tools

Add tools to your agent and grant required permissions in databricks.yml. Use when: (1) Adding MCP servers, Genie spaces, vector search, or UC functions to agent, (2) Permission errors at runtime, (3) User says 'add tool', 'connect to', 'grant permission', (4) Configuring databricks.yml resources.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with concrete, executable code and a clear core workflow, undermined by a progressive-disclosure defect: the heavily-referenced examples/ directory is absent from the bundle. Minor internal redundancy in the closing notes.

Suggestions

Add the missing examples/ directory with the referenced files (uc-function.yaml, uc-connection.yaml, vector-search.yaml, sql-warehouse.yaml, serving-endpoint.yaml, genie-space.yaml, lakebase-autoscaling.yaml, experiment.yaml, app.yaml, custom-mcp-server.md), or remove the table and inline only the snippets that actually exist.

Add an explicit deploy-verification checkpoint to the workflow (e.g., 'databricks bundles validate' before deploy, or confirm the app status after 'bundle run') with a fix-and-retry loop on failure.

De-duplicate the closing 'Important Notes' against the body: remove the value_from and deploy+run restatements, keeping only genuinely new reminders.

Dimension	Reasoning	Score
Conciseness	Mostly lean with code blocks, a table, and short notes, but the 'Important Notes' section repeats the value_from pattern and deploy+run guidance already stated in Steps 2-3; minor trimming possible.	4 / 5
Actionability	Fully executable, copy-paste-ready Python, YAML, and CLI snippets cover the common cases (Genie MCP server, app resource, value_from env, handle_tool_error), with a profile-reminder callout on every databricks command.	5 / 5
Workflow Clarity	A clear three-step sequence (add MCP server, grant access in databricks.yml, deploy and run) with the run step acting as an activation check, but there is no explicit deploy-verification or error-recovery checkpoint, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Sections are well organized and a table signals one-level-deep references to an examples/ directory, but that directory (and the referenced .yaml/.md files) does not exist in the bundle, so the navigation promise is broken; scoring against the actual (empty) bundle structure per the guideline.	3 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that explicitly covers both capability and trigger conditions with concrete user phrases. It is specific to its databricks niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ('Add tools to your agent and grant required permissions in databricks.yml') plus enumerates specific resource types (MCP servers, Genie spaces, vector search, UC functions); minor gaps versus the comprehensive anchor 5.	4 / 5
Completeness	Clearly answers 'what' (add tools and grant permissions in databricks.yml) and 'when' via four explicit numbered trigger conditions including concrete 'User says' phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes explicit natural user phrases ('User says "add tool", "connect to", "grant permission"') and runtime signals ('Permission errors at runtime'), giving good keyword coverage, though it lacks synonyms and file-extension variants for the top anchor.	4 / 5
Distinctiveness Conflict Risk	Niche is clearly databricks agent tool-addition and databricks.yml permission grants with distinct triggers, but 'Configuring databricks.yml resources' is broad enough to risk minor overlap with related deploy/create-tools skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/app-templates
Path: .claude/skills/add-tools-langgraph/SKILL.md
Commit: fdc1b49

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.