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

With no annotations, the description carries the full burden and does well: it discloses the live threshold dependency, a ~20 s wall-clock cap, and the non-deterministic failure mode (found:false) along with recovery advice. It does not state cost/rate-limit or whether the cap is enforced server-side, but the key runtime behaviors are surfaced.

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 dense sentences with the purpose, formula, threshold, and failure/retry advice front-loaded, and zero filler. Every clause carries information an agent needs.

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, so the description must describe returns; it covers found:true/false and the nonce but not the full response shape (e.g., attempts used or achieved bits). For a two-parameter search tool with a stated time cap, it is otherwise complete enough.

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 100% so the baseline is 3, and the description adds a real tradeoff beyond the schema: lowering maxAttempts when difficulty is high. The miner address and nonce role are also embedded in the hash formula, giving contextual meaning to the inputs.

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 and resource (grind a proof-of-work nonce for a miner address), gives the exact hash construction (keccak256(chainId ‖ core ‖ miner ‖ nonce)) and the acceptance criterion (requiredBits leading zero bits). This is precise enough to separate it from the sibling verify_nonce, which would check rather than produce a nonce.

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?

Explains the goal ('so it can mint immediately') and gives failure handling ('may return found:false — retry or lower maxAttempts'). It does not name sibling tools or state when to prefer verify_nonce / get_mining_guide, so it stops short of explicit when-not guidance.

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