Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
88
88%
Does it follow best practices?
Impact
88%
1.95xAverage score across 43 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent picks the most ergonomic tool-registration style for a straightforward String-returning function — the annotated ToolSet path — and registers it correctly. Reaching for the typed Tool<TArgs,TResult> path here would be over-engineering.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Picks the annotated ToolSet style",
"description": "Wraps the function inside a class that implements ToolSet, with @Tool on the method. Does NOT subclass Tool<TArgs,TResult> or ToolBase — those are over-engineering for a String-returning lookup function",
"max_score": 25
},
{
"name": "Annotates parameters with @LLMDescription",
"description": "Each parameter (city, units) has an @LLMDescription explaining what it represents. Without these the generated tool schema is unusable",
"max_score": 20
},
{
"name": "Annotates the class and method with @LLMDescription",
"description": "The ToolSet class itself and the @Tool method each have an @LLMDescription describing what they do (the LLM sees these descriptions)",
"max_score": 15
},
{
"name": "Registers via ToolRegistry DSL",
"description": "Registers the tools using the ToolRegistry { ... } DSL builder, invoking asTools() on a ToolSet instance to bridge into the registry. Not by manually constructing a Map, not by appending after construction",
"max_score": 20
},
{
"name": "Passes the registry into AIAgent at construction",
"description": "Passes the assembled registry as the toolRegistry parameter to AIAgent(...). Does not mutate the agent's registry after construction",
"max_score": 15
},
{
"name": "Does not introduce typed args classes",
"description": "Does not create @Serializable data classes for args or results. The function takes two String parameters and returns a String — the annotated path covers it directly",
"max_score": 5
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
skills
add-observability
add-persistence
add-rag
add-structured-output
add-token-budgeting
add-tool
cache-llm-calls
define-prompt
domain-model-subtask-pipeline
references
enable-prompt-caching
handle-agent-events
manage-state
migrate-from-0-x
model-planner-subtasks
persist-chat-history
query-sql-from-agent
scaffold-agent
snapshot-and-restore
test-koog-agents
trace-agent-internals
use-attachments
use-functional-agent
use-llm-node-variants
use-planner
wire-a2a
wire-acp-server
wire-ktor-server
wire-mcp-server
wire-spring-boot