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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds substantive behavior: no signing, no ledger write, deterministic seeding from the calls themselves for reproducibility, and the fact that the result self-identifies as a sandbox and is excluded from the leaderboard. That is real operational context an agent cannot infer from the structured fields.

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 front-loaded sentences with no filler; the sandbox/no-write constraint leads and the leaderboard caveat closes. The '2,048 coin-flipping monkeys' phrasing is colorful but slightly opaque as a description of the scoring mechanic.

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 low-complexity, read-only tool with full schema coverage and rich annotations, the description covers cost, determinism, and the sandbox flag on the result. With no output schema, it could say a bit more about the shape of the returned score/percentile payload, which is the only remaining gap.

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% and the schema already documents as_of defaults, the 1..200 bound, and each call field's allowed values. The description adds the framing 'unsealed set' but no format or constraint detail beyond what the schema supplies, so the baseline of 3 applies.

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 (score) and resource (an unsealed set of what-if calls) and immediately scopes it as a free, no-signing, no-ledger-write sandbox. It also explicitly distinguishes itself from the sealing path (register_agent -> commit_call), so an agent can tell it apart from commit_call or verify_call without opening any schema.

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 when-to-use case (unsealed what-if calls, reproducible, no cost) and the when-not case (if you want a public percentile, you need an ex-ante sealed call via register_agent -> commit_call) are both stated, and the alternative tools are named explicitly.

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