cpu_withdraw

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers: it reveals that the cell is debited, $CPU is minted, no approve is needed, partial execution can occur if the emission budget is insufficient, it waits for confirmation, and it returns a tx hash. This is exemplary transparency for a mutation tool.

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?

The description is dense but every sentence earns its place: main action, prerequisite, unit constraint, execution behavior, partial-failure case, return result, and lifecycle warning. It is front-loaded with the core action and then layers in essential edge cases without repetition.

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?

Given there is no output schema, the description appropriately explains the return value (tx hash) and the result's split of requested versus executed amounts. It also covers prerequisite authentication, ownership, approval requirements, and balance-check follow-up. Nothing needed for correct invocation is missing.

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 meaningful context beyond the schema: amount is in whole wCPU units, must not exceed the cell's balance, and tokenId refers to a cell the caller owns. It reinforces the 1:1 conversion and partial-execution behavior, making parameter usage clear even without opening the schema.

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?

The description opens with a specific verb and resource: 'Cash out a cell's wCPU ... to the on-chain $CPU token in your wallet, 1:1.' This clearly separates it from sibling tools like cpu_swap, cpu_mint_cell, and cpu_get_balance. The scope is exact and immediately actionable.

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 description gives strong contextual usage guidance: it requires cpu_authenticate first, requires cell ownership, and warns to withdraw before selling the cell. It does not explicitly name alternative tools or state when not to use it, but the use case is unambiguous enough that no exclusion is needed.

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