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

With no annotations, the description carries the full behavioral burden; it does disclose the commit-reveal protocol and the reproducibility requirement, which is real value. It still omits whether the call is read-only, whether the same inputs deterministically reproduce the output, and whether any server-side state (round) is created, which matters for a randomness tool.

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 tight sentences with zero padding; the mechanism is front-loaded and the usage and follow-up guidance follow in priority order.

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?

No output schema, so the description correctly states the return is a random integer, and it explains the protocol needed to verify it. It is close to complete for a 5-optional-param tool, with only deterministic/purity behavior left unstated.

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 min, max, nonce, round and client_seed are already documented individually. The description adds the framing that the seed is committed and must later be revealed, which only marginally enriches client_seed beyond the schema.

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?

States a specific verb+resource ('provably-fair random integer from a committed seed') with the commit-reveal mechanism named, so the operation is unambiguous. It does not, however, distinguish itself from the sibling fair_pick, which an agent would likely confuse it with.

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 concrete use cases ('verifiable winner selection, raffles and allocations') and a post-call workflow ('Reveal the seed afterwards so anyone can reproduce the result'). It stops short of exclusions or naming alternatives such as fair_pick, so the when-not side 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.