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.

69

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 highly actionable with executable code and a clear workflow, but it lacks a deploy/validation checkpoint and references an examples/ directory that is absent from the bundle.

Suggestions

Add a validation checkpoint after `databricks bundle run` (e.g., check app logs or confirm the MCP tools list is populated) to turn the deploy step into a validate-fix-retry loop.

Create the referenced `examples/` directory with the listed YAML/md files, or inline the few most-used snippets so no referenced path is broken.

De-duplicate the value_from guidance: state the 'must match a resource name' rule once and remove the redundant 'IMPORTANT' and 'Critical' restatements plus the notes bullet.

DimensionReasoningScore

Conciseness

Mostly lean with tight code blocks and a compact table, but the value_from rule is restated three times and deploy+run is repeated in the notes, so minor trimming is possible.

4 / 5

Actionability

Provides copy-paste-ready Python with real imports, complete databricks.yml YAML blocks, concrete CLI commands, and specific error-handling kwargs covering the common cases.

5 / 5

Workflow Clarity

A clear three-step sequence (add server, grant access, deploy+run) exists, but there is no explicit validation or verification checkpoint for the deploy operation, capping this dimension per the batch-operation guideline.

3 / 5

Progressive Disclosure

Structure and signaled one-level-deep references to an examples/ directory are good, but the referenced examples/ files do not exist in the bundle, breaking navigation.

3 / 5

Total

15

/

20

Passed

Description

96%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, specific description that explicitly covers both capability and triggers with natural user phrases. Only weakness is the unaddressed boundary with the sibling create-tools skill.

DimensionReasoningScore

Specificity

Names concrete actions ('Add tools to your agent and grant required permissions in databricks.yml') plus specific resource types (MCP servers, Genie spaces, vector search, UC functions), giving comprehensive coverage.

5 / 5

Completeness

Clearly states what the skill does and follows with a numbered 'Use when:' list of four concrete trigger scenarios, explicitly answering both what and when.

5 / 5

Trigger Term Quality

Explicitly quotes natural user phrases ('add tool', 'connect to', 'grant permission') and adds symptom-based triggers ('Permission errors at runtime') alongside domain keywords.

5 / 5

Distinctiveness Conflict Risk

Databricks-specific niche with distinct triggers minimizes conflict, but the description does not sharply distinguish 'add tools' from the sibling 'create-tools' skill, leaving minor overlap risk.

4 / 5

Total

19

/

20

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.