send_token

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

Annotations only include 'openWorldHint: true', which is vague. The description adds that the tool can send both native and ERC20 tokens and emphasizes base units, but it omits critical behavioral details such as irreversibility, the need for wallet funds, transaction confirmation, or gas implications. For a state-changing operation like sending funds, this is insufficient disclosure.

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 a single concise sentence that front-loads the action ('Send') and quickly specifies the resource and recipient. Every word is necessary, with no fluff or repetition. It earns a perfect score for efficiency.

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 the sensitivity of transferring funds, the description is incomplete. It does not mention prerequisites (e.g., active wallet, sufficient balance), consequences (irreversible transaction), or how the optional chainId and tokenAddress parameters affect the operation. While the schema covers parameter syntax, the description lacks the necessary contextual warnings and usage constraints for a tool that moves value.

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?

The schema has 100% coverage, so each parameter is documented. The description's mention of 'base units' is already present in the schema's description of amountInBaseUnits, so it adds no new meaning. It does not clarify parameter relationships beyond what the schema already states, keeping the score at the baseline.

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 clearly states the tool's function: 'Send native currency or an ERC20 token to a recipient, in base units.' It uses a specific verb ('send'), identifies the resource (native currency/ERC20), and mentions the recipient. However, it does not explicitly distinguish itself from sibling tools like 'transfer' or the EVM-specific transfer tools, so it lacks explicit sibling differentiation.

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?

There is no guidance on when to use this tool versus alternatives. Given the presence of multiple transfer-related siblings (e.g., evm_transfer_native, evm_transfer_erc20, transfer), the description does not clarify whether this tool should be preferred for cross-chain operations or when both native and ERC20 sends are possible. No exclusions or alternative recommendations are provided.

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