tools

Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, create tool definitions, and attach them to config variations.

Quality

60%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/tools/SKILL.md

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability and workflow clarity — the 4-step process is well-defined with concrete MCP tool calls, JSON examples, and explicit verification steps. However, it suffers from poor progressive disclosure: the provider conversion table, conversion snippets, and agent loop skeleton are all inlined, making the document very long. These reference sections should be split into separate files, with the SKILL.md providing a concise overview and links.

Suggestions

Move the per-provider schema conversion table and Python snippets into a separate reference file (e.g., PROVIDER-SCHEMAS.md) and link to it from the main skill.

Move the 'Agent loop with tool calls' section (skeleton code and stop-reason details) into a separate reference file (e.g., AGENT-LOOP.md) since it's supplementary to the core tool-creation workflow.

Add a brief 'Quick start' summary at the top (5-10 lines) that shows the minimal happy path before diving into detailed steps.

Dimension	Reasoning	Score
Conciseness	The skill is fairly long with substantial reference material (provider conversion tables, full agent loop skeletons, per-provider snippets) that could be split into reference files. The core workflow is reasonably tight, but the provider-specific conversion code and agent loop section add significant bulk that most users won't need inline.	2 / 3
Actionability	The skill provides fully executable code snippets for tool creation schemas, variation attachment payloads, provider-specific conversion code, and a complete agent loop skeleton. The MCP tool calls are clearly specified with exact parameter names and JSON examples.	3 / 3
Workflow Clarity	The 4-step workflow (Identify → Create → Attach → Verify) is clearly sequenced with explicit verification in Step 4. The skill includes important guardrails like 'Create Before Attach,' warns against bundling extra fields in PATCH calls, and provides an explicit ordered sub-workflow for the discovery case. Edge cases are documented in a table.	3 / 3
Progressive Disclosure	Despite referencing external files (built-in-metrics tracking docs, related skills), the skill inlines extensive provider-specific conversion snippets, a full agent loop skeleton, and a large provider table that would be better placed in separate reference files. The body is monolithic at ~200+ lines with no bundle files to offload to, making it a wall of content.	1 / 3
	Total	9 / 12 Passed

Description

50%

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 communicates the general domain (agent tool/function calling setup) and lists some actions, but remains somewhat vague in its specifics and lacks an explicit 'Use when...' trigger clause. It also uses second person ('Helps you'), which is discouraged. The trigger terms are reasonable but incomplete, missing common user phrasings.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to add tools or function calling to an agent, define tool schemas, or configure agent capabilities.'

Replace second person ('Helps you identify') with third person ('Helps identify what an agent needs to do' or 'Creates tool definitions and attaches them to config variations').

Include more natural trigger terms users might say, such as 'tool use', 'tool schema', 'JSON schema', 'API tools', or 'agent setup'.

Dimension	Reasoning	Score
Specificity	Names the domain (agent tools/function calling) and some actions ('identify what your agent needs to do, create tool definitions, attach them to config variations'), but the actions are somewhat vague—'identify what your agent needs to do' is abstract rather than concrete.	2 / 3
Completeness	Answers 'what' (create tool definitions, attach to config variations) but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes relevant keywords like 'tools', 'function calling', 'tool definitions', and 'config variations', but misses common user variations like 'API tools', 'tool use', 'tool schema', 'JSON schema', or 'agent configuration'. Coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The mention of 'tools (function calling)' and 'config variations' provides some specificity, but 'agents' and 'capabilities' are broad terms that could overlap with general agent-building or configuration skills.	2 / 3
	Total	8 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: launchdarkly/ai-tooling
Commit: 913b745

Reviewed: 10 days 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.