ygo_export_selfplay

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

No annotations are supplied, so the description carries the full burden. It does valuable work by disclosing the exported record schema (since no output schema exists) and by noting games run on the real engine, but it omits key behavior: that the tool writes files to outPath and may overwrite, and how long a 5-game, 5000-step run takes. Nothing here contradicts the tool, but mutation and cost side effects go unstated.

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?

Two sentences, zero filler, with the core action and the exported format front-loaded ahead of the training-data rationale. Nothing could be cut without losing information.

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?

With eight parameters, no annotations, and no output schema, the description does the important thing: it specifies what each exported record contains and where it lands, which is exactly what an agent cannot get from structured fields. The remaining gap is runtime and file-side-effect behavior for a potentially long batch run.

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 coverage is 75%, so the schema already explains seed, deckA, deckB, games, outPath, and maxSteps. The description adds no parameter meaning at all, and it never addresses extraA/extraB, the two undocumented params, nor how "policy-vs-policy" is selected when no policy parameter exists in the schema. Baseline 3 is warranted given the schema does most of the work.

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 gives a specific verb and resource: plays policy-vs-policy games on the real engine and exports each decision as JSONL, and it names the payload fields (request type, legal option codes, chosen action, result). That distinguishes it from sibling duel tools like ygo_run_duel or ygo_simulate_duel_scenario by framing it as a training-data generator, though it never names those siblings 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?

"This is the training-data generator for behavioural cloning / reinforcement learning" implicitly tells the agent when to reach for it, but there is no explicit when-not guidance and no named alternative for plain single-duel simulation or benchmarking. The agent must infer the boundary from the sibling list.

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