prepare_token_send

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

Annotations indicate destructiveHint=true (modifies state) and idempotentHint=true (same input produces same output). The description adds that the transaction is unsigned, the 'max' amount is resolved at build time, and token disambiguation is needed. No contradictions with annotations.

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?

Two sentences, front-loaded with the purpose. The first sentence clearly states the action, the second adds critical usage context. No unnecessary words or 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?

The description covers the core function and key usage notes, but lacks information about the return value (e.g., unsigned transaction object). Given that there is no output schema, the description should clarify what the tool returns. The chain enum and other parameters are not elaborated.

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 input schema has 5 parameters with only 20% description coverage (only 'amount' has a schema description). The description adds that 'amount' is human-readable and accepts 'max', but does not explain 'wallet', 'chain', 'token', or 'to' beyond what the schema provides. The suggestion that 'token' could be a symbol conflicts with the schema requiring a 0x address.

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 'Build an unsigned ERC-20 transfer transaction,' specifying the verb (build), resource (unsigned ERC-20 transfer), and special behavior for 'amount: "max"'. This distinguishes it from sibling tools like prepare_native_send or prepare_solana_spl_send.

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 explicit guidance on when to use this tool (ERC-20 transfers) and a key prerequisite: if the user names a token by symbol, call resolve_token first to disambiguate variants (e.g., USDC vs USDC.e). It also advises to surface warnings to the user. However, it does not provide negative usage guidance (e.g., not for native sends).

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