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.

65

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./agent-langgraph-advanced/.claude/skills/add-tools/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 concrete code, but it loses points for repeated content and, more importantly, for pointing to an examples/ directory and named files that are not present in the skill bundle, breaking progressive disclosure.

Suggestions

Ship the referenced `examples/` files (uc-function.yaml, genie-space.yaml, custom-mcp-server.md, etc.) in the bundle, or remove the file table and inline the essential snippets.

De-duplicate the 'value_from matching' and 'Deploy + Run after changes' guidance so each appears once, and fix the inconsistent app name (agent_langgraph vs agent_langgraph_advanced).

Add an explicit post-deploy verification step (e.g., confirm the tool is callable by the agent) to close the workflow_clarity checkpoint gap.

DimensionReasoningScore

Conciseness

Largely lean with executable code blocks and a focused table, but 'value_from matching' and 'Deploy + Run after changes' are each stated twice (once in the body, once in Important Notes), which is minor padding that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready Python, YAML, and bash blocks for each step; minor gaps remain (undefined `host`, placeholder UUIDs, and an inconsistent app name `agent_langgraph` vs `agent_langgraph_advanced`) that keep it just below fully executable.

4 / 5

Workflow Clarity

A clear three-step sequence (add MCP server -> grant access in databricks.yml -> deploy and run) with an error-handling section, but there is no explicit post-deploy verification that the tool actually works, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

Sections are well-organized and references are clearly signaled via a file table, but the referenced `examples/` directory and files (e.g. `examples/custom-mcp-server.md`, `uc-function.yaml`) do not exist in the bundle, so the navigation links do not resolve.

3 / 5

Total

15

/

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 concretely states both what it does and when to use it with explicit enumerated triggers. The main deduction is the second-person 'your agent' phrasing, which the rubric penalizes on specificity.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Add tools to your agent and grant required permissions in databricks.yml', 'Adding MCP servers, Genie spaces, vector search, or UC functions'), which would be a 5, but the second-person phrasing 'your agent' triggers the one-point specificity penalty per the rubric guidelines.

4 / 5

Completeness

Clearly states the 'what' ('Add tools ... grant required permissions in databricks.yml') and an explicit enumerated 'Use when: (1)...(2)...(3)...(4)...' clause with concrete triggers, matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural trigger phrases including the explicit user-quotes 'add tool', 'connect to', 'grant permission' plus 'Permission errors at runtime'; falls just short of 5 because it lacks synonym/file-extension breadth.

4 / 5

Distinctiveness Conflict Risk

The databricks.yml/MCP niche is mostly distinct with clear triggers, but the closely related create-tools skill creates minor overlap risk, fitting the 'mostly distinct' anchor rather than a clean 5.

4 / 5

Total

17

/

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.