Check a wallet for stuck stablecoins

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

Annotations already cover read-only/idempotent/non-destructive, but the description adds material behavior beyond them: the definition of 'stuck' (not enough gas to move the tokens), the per-chain partial-failure signal ('a chain that did not answer has error: true'), and the hard blocker that frozen tokens are unfixable by any available tool. That is exactly the mutation/failure context an agent needs before chaining into a rescue flow.

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-loaded with the purpose, then usage, then the safety note, then the return shape — a sensible order with no filler. The single long paragraph is dense and the inline return signature is syntactically heavy, but no sentence is disposable given there is no output schema.

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?

With no output schema, the description compensates by spelling out the return object and the per-chain error flag. Combined with the stuck/frozen semantics and the pointer to quote_send/quote_swap, an agent has everything needed to call it and act on the result.

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% and the address-format guidance (0x…, base58, T…) is already in the schema, so the description gets no credit there. It does add one thing the schema does not say: the address is checked on every chain 'where it is valid', implying per-chain applicability filtering rather than a uniform sweep.

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 ('Checks one address on every supported chain') and enumerates exactly what it reports: stablecoin holdings, gas balance, stuck status and issuer freeze. An agent can distinguish it from quote_send/quote_swap/get_transfer 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?

Explicitly routes usage: 'Use it before quote_send or quote_swap to find the chain and token to rescue', naming the downstream siblings and the condition that selects them. It also states the exclusion case — a frozen token cannot be moved by any tool here, only the issuer can lift it — so the agent knows when to stop rather than trying further tools.

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