CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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 executable code and a clear 3-step workflow. Its main weaknesses are a missing explicit validation/feedback loop and advertised bundle references (examples/) that are not present in the skill directory.

Suggestions

Add an explicit validation checkpoint in the workflow (e.g., after granting access, verify the agent can reach the resource or check `databricks bundle validate` output, then fix-and-retry) to lift workflow_clarity to 3.

Either include the referenced `examples/` directory with the listed YAML/MD files or remove the dangling references and inline the essential snippets so navigation actually resolves, improving progressive_disclosure.

DimensionReasoningScore

Conciseness

Lean and efficient: it assumes competence with a one-line "Profile reminder" block, numbered steps, and executable snippets without explaining what MCP or Databricks is. Every section earns its tokens, matching the level-3 anchor rather than the level-2 'good library that handles...' style.

3 / 3

Actionability

Provides fully executable Python (McpServer/Agent wiring) and YAML resource snippets, concrete commands ("databricks bundle deploy"), a pinned CLI version (v0.298.0+), and a tunable timeout=60.0 example — copy-paste ready per the level-3 anchor.

3 / 3

Workflow Clarity

The 3-step sequence (add MCP server -> grant access -> deploy) is clearly ordered, but there is no explicit validate/verify checkpoint or fix-and-retry feedback loop for a permission-sensitive operation; "you MUST grant... Without this, you'll get permission errors" is a warning, not a validation loop, matching the level-2 'steps listed but validation gaps' anchor.

2 / 3

Progressive Disclosure

It signals one-level-deep references well via an examples/ table and custom-mcp-server.md plus sibling skills, but the referenced examples/ bundle is absent from the skill directory (no references/, scripts/, assets/, or examples/), so the navigation it advertises does not resolve — capping this at the level-2 anchor rather than level-3.

2 / 3

Total

10

/

12

Passed

Description

100%

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

The description is concise yet specific, clearly stating both the concrete actions it performs and the explicit 'Use when' triggers. It is well-differentiated within the Databricks-agent niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Add tools", "grant required permissions in databricks.yml", "Adding MCP servers, Genie spaces, vector search, or UC functions"), matching the level-3 anchor rather than the level-2 partial-coverage anchor.

3 / 3

Completeness

Explicitly answers both what (add tools / grant permissions in databricks.yml) and when ("Use when: (1)... (4)...") with explicit triggers, matching the level-3 anchor and exceeding the level-2 "what but no when" anchor.

3 / 3

Trigger Term Quality

Includes natural phrases a user would actually say ("User says 'add tool', 'connect to', 'grant permission'", "Permission errors at runtime"), giving good coverage rather than just one or two keywords.

3 / 3

Distinctiveness Conflict Risk

Scoped to a Databricks-agent niche with distinct, specific triggers (MCP servers, Genie spaces, databricks.yml), making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
databricks/app-templates
Reviewed

Table of Contents

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.