Name: add-tools
Rating: 72 (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

87%

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

75%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.

The body is actionable and well-sequenced with executable examples, but its progressive disclosure is undermined by extensive references to an examples/ bundle that is not present. A minor inconsistency (agent_langgraph vs agent_non_conversational in the run command) also slightly weakens execution guidance.

Suggestions

Provide the referenced examples/ directory (uc-function.yaml, genie-space.yaml, custom-mcp-server.md, local-python-tools.md, etc.) or remove the table and inline the essential snippets, since the bundle is currently missing.

Add a verification checkpoint after deploy+run (e.g., confirm the agent can invoke the tool without a permission error) to close the workflow loop for a permission-sensitive skill.

Resolve the app-name inconsistency between 'databricks bundle run agent_langgraph' (Step 3) and 'agent_non_conversational' (Important Notes) so the run command is unambiguous.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable code blocks and minimal concept explanation, but the 'Important Notes' section restates points already made (deploy+run, value_from matching), adding minor redundancy.	4 / 5
Actionability	Provides copy-paste-ready Python, YAML, and bash snippets covering the common cases (MCP server setup, databricks.yml grant, deploy+run, error handling), all concrete and executable.	5 / 5
Workflow Clarity	A clear three-step sequence (add server, grant access, deploy+run) with inline code, but lacks an explicit post-deploy verification that the permission grant took effect and the agent can call the resource.	4 / 5
Progressive Disclosure	The body is well-sectioned and signals references to an examples/ directory and several files (custom-mcp-server.md, local-python-tools.md, plus 10 YAML files), but none of these bundle files actually exist, so the referenced detail is unreachable.	2 / 5
	Total	15 / 20 Passed

Description

100%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, third-person description that concretely states both the action and the trigger conditions with explicit 'Use when' guidance. It is specific, distinctive, and avoids fluff.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Add tools to your agent and grant required permissions in databricks.yml') and enumerates the specific resource types (MCP servers, Genie spaces, vector search, UC functions), giving comprehensive coverage of its domain.	5 / 5
Completeness	Clearly states what it does (add tools + grant permissions in databricks.yml) and provides an explicit 'Use when:' clause with four concrete numbered triggers, answering both what and when.	5 / 5
Trigger Term Quality	Explicitly quotes natural user phrases ('add tool', 'connect to', 'grant permission') alongside runtime signals ('Permission errors at runtime'), covering the natural terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (tool wiring + permission grants in databricks.yml for agents) with distinct triggers; minimal overlap risk with adjacent skills like create-tools or deploy.	5 / 5
	Total	20 / 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: agent-non-conversational/.claude/skills/add-tools/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.