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

Annotations declare readOnlyHint and openWorldHint, and the description adds substantial context beyond them: reads directly from chain (works for wallets that never signed in), names escrowsChecked reporting, explains unsigned-transaction return shape, states the service never signs or holds keys, warns the user must approve and that the mined transaction is irreversible, and flags Base Sepolia testnet with no monetary value.

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?

Front-loads the core verb and then uses SCOPE and NETWORK sections to organize the constraints, which keeps a long description navigable. Some sentences are verbose, but nearly all carry decision-relevant information about week ids, irreversibility, and the testnet caveat.

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, yet the description explains the return shape ({to, data, value}), the range of weeks scanned, and the deployment-scoping limits, so an agent has everything needed to call it correctly and interpret the result. The network and irreversibility warnings close the remaining gaps for a read-only tool that produces a claimable transaction.

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, but the description adds real semantic depth: weekId is a CONTRACT week id that resets on redeployment, is reported by luckdrop_get_results, and when omitted triggers a 26-week scan whose exact range is returned. This clarifies the meaning and interaction of the optional parameter beyond its schema text.

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 precise verb and resource: checking whether a wallet has won an uncollected prize and returning a claim transaction. It also distinguishes its role from siblings by naming luckdrop_get_results as the source of the CONTRACT week id, so an agent can tell which tool produces the week ids versus which one consumes them.

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 clear usage conditions: with no weekId it scans the last 26 contract weeks, and an explicit weekId reaches an older week on those escrows. It also states when the tool will NOT succeed (prizes in an escrow from an earlier deployment). It stops short of explicitly naming the sibling that should be used instead for adjacent tasks, so it is strong context rather than full alternative routing.

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