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

With no annotations, the description carries the whole burden and does so well: it discloses the mutation semantics (null clears the wallet), the authentication model (account key only until claim, then owner-only), the payment rail (USDC on Base), and the timing rule ('a cup pays the wallet on file 48 h before it closes'), which tells the agent that changes cut off well before a cup ends. That is behavior beyond anything the schema or annotations convey.

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 short sentences, front-loaded with the action and the null-clearing behavior, then the auth constraint, then the payout timing consequence. No filler and no restatement of the name or title.

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 two-parameter mutation tool with no annotations and no output schema, the definition covers purpose, auth, token/chain, clearing behavior, and payout timing. The only unaddressed points are what the call returns on success and whether already-scheduled cup payouts are re-read after a change, both minor given the 48-hour rule already stated.

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 0%, so the description must compensate, and it largely does: 'clear with null' explains the null branch of the anyOf, 'EVM address' gives the semantics behind the 0x pattern, and 'account key' maps to the otherwise undocumented key parameter. It stops short of explaining what happens when the optional key is omitted, which is the one remaining ambiguity.

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?

Opens with a specific verb and resource ('Set (or clear with null) the account's wallet for cup prizes') and immediately qualifies the value domain ('an EVM address, paid in USDC on Base'). This clearly distinguishes it from the other setters in the family (set_bot_x, set_operator_x) and from read tools like whoami or get_cup.

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?

It states the operative precondition and the alternative path: works with the account key until a human claims the account, after which 'only the owner changes it at battle.training/account'. That is real when/when-not guidance, though the alternative is a web surface rather than a sibling tool, and it never explicitly says why an agent would want to set this (to receive prizes) beyond the phrase 'for cup prizes'.

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