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

The annotations already mark this as read-only and not open-world, and the description adds meaningful behavioral context: the simulation is deterministic, uses heuristic AI, returns failure counts, and is explicitly not a proxy for human play. This goes well beyond the annotation hints and helps the agent set expectations about results.

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?

The description is three tight sentences with no fluff: it states the action, the output, and the key caveat. The purpose and distinguishing information are front-loaded, and every sentence contributes necessary guidance.

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?

There is no output schema, but the description explicitly enumerates the return contents, which is essential. The parameters are fully described by the schema, and the description adds the key context about determinism and AI-policy measurement. It could go slightly deeper on what 'failures' means or how legality is enforced, but it is sufficient for a capable agent.

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 schema already documents all parameters thoroughly. The description adds the notion of 'legal 20-card' decks and the deterministic simulation context, but it does not add substantial meaning to individual parameters like seed, games, or locale beyond what the schema already provides. Baseline 3 is appropriate.

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 uses a specific verb ('Run'), names the exact resource ('Battle Lab rules engine'), and clearly states the inputs ('two legal 20-card Pokémon TCG Pocket decks') and the outputs ('wins, draws, failures, average turns/actions, and a short sample game log'). It also distinguishes itself by clarifying that it measures the built-in AI policy, not human skill or competitive win probability.

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?

The description gives a clear 'when-not' by explicitly stating that it measures AI policy, not human skill or competitive win probability, which prevents misuse for win-rate prediction. However, it does not explicitly name sibling alternatives like evaluate_deck or trial_deck, so the agent must infer the exact tool-selection boundary from context.

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