Send Crypto (EVM)

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

Annotations already indicate destructive, non-read-only behavior; the description adds meaningful operational context: automatic native-vs-ERC20 routing, the requirement for a runtime PIN that must never be stored or logged, and the need for user confirmation before sending. It also discloses the return shape including txHash, which is important since no output schema is present.

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 organized with a clear main statement, a routing rule, numbered pre-call steps, labeled Args, a Returns block, and examples. It is detailed but every section contributes actionable information; nothing is redundant or filler.

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 financial transfer tool with destructive behavior and no output schema, the description covers everything an agent needs: prerequisites, PIN handling, user confirmation, routing rules, parameter semantics, return values, examples, and security guidance. The sibling context is complex, but the description fully positions this EVM send operation.

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?

Input schema coverage is 100%, giving a strong baseline. The description adds value beyond the schema by explaining the reason for using a string amount ('to avoid floating point errors'), clarifying when to include or omit tokenAddress, and providing concrete chainId examples for ETH, BSC, and MATIC.

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: 'Sends cryptocurrency from the user's Monei EVM wallet to an external wallet address.' It further distinguishes the tool's scope by explaining it handles both native tokens and ERC-20s, and the EVM qualifier separates it from the Solana sibling tool.

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 clear operational guidance: check balance with monei_get_evm_portfolio, ask for the transaction PIN at runtime, and obtain explicit user confirmation before sending. It does not explicitly state when not to use this tool versus alternatives like send_crypto_solana or swap_tokens_evm, so it falls just short of a 5.

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