Name: add-tools
Rating: 64.8 (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

78%

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 ./agent-langchain-ts/.claude/skills/add-tools/SKILL.md

Quality

Content

68%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.

Highly actionable content with strong executable examples, but it would benefit from tightening duplicated code and notes and from adding a post-deploy verification step. Referenced bundle files are well signaled but missing from the directory.

Suggestions

Collapse the two getMCPServers code blocks into one and remove the 'Important Notes' items that repeat earlier content to reduce token bloat.

Add an explicit post-deploy validation checkpoint (e.g. confirm the tool is callable / permissions took effect) to satisfy the destructive/batch-operation cap.

Provide the referenced bundle files (examples/*.yaml, custom-mcp-server.md, mcp-known-issues.md, mcp-best-practices.md) so the one-level-deep references resolve.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with code and tables, but tightened scope is hurt by a duplicated getMCPServers example (Step 1 vs the 'TypeScript-Specific Patterns' section) and an 'Important Notes' list that restates points already made earlier (Genie CAN_RUN, deploy after changes, service principal).	3 / 5
Actionability	Fully executable, copy-paste-ready TypeScript, YAML, and bash snippets cover the common cases (Genie, SQL, UC functions, vector search, custom MCP apps, permission grants) with concrete imports, real paths, and appropriate placeholders.	5 / 5
Workflow Clarity	The main workflow has a clear Step 1 -> Step 2 -> Step 3 (deploy) sequence, but there is no validation/verification checkpoint after deploying or granting permissions, and the troubleshooting guidance is separate rather than an integrated feedback loop.	3 / 5
Progressive Disclosure	Good structure with clearly signaled, one-level-deep references (an examples/ table, custom-mcp-server.md, mcp-known-issues.md, mcp-best-practices.md, the deploy skill); the gap is that none of these referenced bundle files actually exist in the evaluated skill directory, so the references cannot be verified.	4 / 5
	Total	15 / 20 Passed

Description

87%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 triggering conditions with natural user-say phrases. The main weakness is second-person voice ('your agent') instead of the recommended third person.

Suggestions

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

Add a few synonym trigger terms (e.g. 'MCP', 'tools', 'enable tool') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (add MCP servers, Genie spaces, vector search, UC functions; grant permissions in databricks.yml; configure resources) with comprehensive domain coverage, which would be a 5, but reduced by 1 because the opening 'Add tools to your agent' uses second-person ('your') instead of third person.	4 / 5
Completeness	Clearly answers both 'what' (add tools and grant permissions in databricks.yml) and 'when' via an explicit four-item 'Use when' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural trigger coverage with explicit user-say quotes like "add tool", "connect to", "grant permission" plus "Permission errors at runtime"; falls just short of 5 because synonym variety is limited and there are no file-extension-style triggers.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear Databricks-specific niche (databricks.yml, MCP servers, Genie spaces, UC functions) with distinct triggers and minimal overlap with unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks/app-templates
Path: agent-langchain-ts/.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.