ygo_run_duel

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose genuine behaviour: the engine executes Lua card scripts and handles chain/cost/target/timing, and it returns a message timeline. It does not cover determinism, cost/latency of running up to maxSteps engine steps, error behaviour on invalid decks, or that the default responder is passive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence, front-loaded with the verb and the engine identity, and every clause (Lua scripts, chain/cost/target/timing, message timeline) adds information. Slightly long but there is no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter tool with no output schema, the description usefully summarises the return value (draw, summon, chain, LP update, win), which fills the biggest gap. However, it says nothing about how the alternative deck-input parameters relate to each other or about failure modes, so it is only adequately complete for this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 and the schema already explains every parameter including the ydke/ydk formats, seeds, and step budgets. The description adds no parameter-level guidance, notably leaving the deck vs deckA vs opponentDeck vs deckB overlap unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Run') and resource ('a REAL duel') and scopes it to the ocgcore-wasm engine, so the agent knows this actually executes the game rather than analysing it. It implicitly contrasts with lighter simulation siblings ('REAL'), but never names ygo_simulate_duel_scenario or ygo_ai_benchmark explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the word 'REAL' and the mention of the full engine executing Lua scripts; there is no explicit when-to-use or when-not-to-use statement. Given ~50 sibling tools including ygo_simulate_duel_scenario and ygo_ai_benchmark, the boundary between them is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.