Name: add-tools
Rating: 61.6 (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

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-tools-openai/SKILL.md

Quality

Content

65%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 concise and highly actionable with concrete code and a clean workflow, but it lacks validation checkpoints after the deploy step and references an examples/ bundle directory that is not actually present, undermining both workflow clarity and progressive disclosure.

Suggestions

Add an explicit verification step after deploy, e.g. 'Confirm the agent can invoke the tool; if a permission error appears, re-check the databricks.yml resources entry and redeploy.'

Ship the referenced examples/ files (uc-function.yaml, custom-mcp-server.md, etc.) or inline the essential snippets so the table's references resolve to real content.

Tighten the MCP error-handling paragraph by leading with the actionable timeout parameter rather than the SDK's default behavior.

Dimension	Reasoning	Score
Conciseness	The body is lean and code/table-driven with minimal padding; only minor instances of over-explanation (e.g. 'The OpenAI Agents SDK catches tool errors by default and returns the error message to the LLM') could be trimmed, fitting anchor 4.	4 / 5
Actionability	Provides copy-paste-ready code (McpServer + Agent construction, databricks.yml YAML, timeout config) and concrete commands ('databricks bundle deploy'), with only minor gaps from placeholders ({{BUNDLE_NAME}}, space_id) and deferring full snippets to the examples/ directory, matching anchor 4.	4 / 5
Workflow Clarity	A clear three-step sequence (add MCP server, grant access, deploy) is present, but there are no validation/verification checkpoints after the permission-grant and deploy steps (e.g. confirming the agent can actually call the tool), which fits the anchor-3 'sequence present but checkpoints missing' and the validation-gap guidance for risky operations.	3 / 5
Progressive Disclosure	Structure is well-intended with a concise overview, a clear resource-type table, and one-level-deep references to examples/ files and sibling skills; however the referenced bundle files (examples/uc-function.yaml, examples/custom-mcp-server.md, etc.) do not exist in the bundle, so the navigation does not resolve, pulling it down from a structural 4 to anchor 3.	3 / 5
	Total	14 / 20 Passed

Description

78%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 well-constructed description that clearly states what the skill does and when to use it, with strong natural-language triggers and a distinct Databricks niche. The main weakness is second-person voice ('your agent'), which costs a specificity point.

Suggestions

Rewrite in third person to avoid the second-person voice penalty, e.g. 'Adds tools to an agent and grants required permissions in databricks.yml.'

Add common synonyms/file extensions (e.g. '.yml', 'MCP', 'tools') to push trigger-term coverage toward anchor 5.

Sharpen the 'what' beyond two core actions by listing the concrete resource operations (add, grant, configure, deploy) to lift specificity.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('Add tools to your agent and grant required permissions in databricks.yml', 'Configuring databricks.yml resources') plus an enumerated set of resource types (MCP servers, Genie spaces, vector search, UC functions), which is a solid anchor-4 base; reduced by 1 for second-person voice ('your agent'), per the voice guideline.	3 / 5
Completeness	Explicitly answers both 'what' (add tools and grant permissions in databricks.yml) and 'when' (a four-item 'Use when:' list of concrete trigger conditions), matching the anchor-5 example of clearly answering both with concrete triggers.	5 / 5
Trigger Term Quality	Strong keyword coverage including directly-quoted natural user phrases ("User says 'add tool', 'connect to', 'grant permission'") plus 'Permission errors at runtime'; a few synonyms or file extensions are missing, so it sits at anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Databricks-specific niche (databricks.yml, MCP servers, Genie spaces, UC functions) with distinct permission-granting triggers gives minimal conflict risk; minor overlap with the sibling create-tools skill keeps it at 4 rather than 5.	4 / 5
	Total	16 / 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-openai/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.