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

Annotations already declare readOnly/idempotent/closed-world, so the description's added value is the mechanics: deterministic replay of the provably fair algorithm, a per-bet result and multiplier, and the SHA-256 hash returned for comparison against the pre-reveal hash Stake published. The prerequisite that only revealed seeds work is meaningful behavioral context. It stops short of describing error behavior for mismatched seeds or invalid option combinations.

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?

Three sentences with no waste: purpose and cap first, then the verification hash return, then the seed-reveal prerequisite. Front-loaded and each sentence adds distinct 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?

An output schema exists, so return-shape explanation is optional, yet the description still calls out the SHA-256 comparison value, which is the crux of verification. The only gap is guidance on constructing the game-dependent `options` payload for the 29 supported games.

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 67%, so most parameters are already documented, and the description only reinforces serverSeed/clientSeed/nonce and the 200-nonce cap on count. The large game-specific `options` object — where wrong settings silently change the replay — gets no explanation in the description beyond what the schema's own summary says.

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?

Names a specific verb and resource: replays Stake Originals bets from a revealed server seed, client seed and nonce using Stake's provably fair algorithm, and reports results and multipliers. This is clearly distinct from the sibling set (stake_seed_hunt_odds, stake_hilo_path, stake_crash_odds), which estimate odds or paths rather than verifying actual bet outcomes.

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?

Gives a clear precondition for use: it needs the unhashed server seed, which Stake only reveals after the seed pair is rotated. It also states the throughput limit of 200 nonces per call. It does not explicitly name when to prefer a sibling tool, but the verification framing makes the boundary reasonably obvious.

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