prepare_transaction

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

No annotations provided, so description carries full burden. It explicitly states read-only behavior, never signs or submits, and defaults to testnet. It warns about potential mainnet account issues. No contradictions.

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?

Three sentences, front-loaded with the main action. Somewhat dense but still clear. Could be slightly more structured, but no fluff.

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?

Missing description of return value (modified transaction JSON) and error cases beyond actNotFound warning. No output schema, so description should cover that. Overall adequate but incomplete.

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 low (33%), but description explains the tx parameter (must include Account + TransactionType), the network parameter (default testnet, use mainnet for mainnet accounts), and lastLedgerOffset implied in 'now + offset'. Adds significant meaning beyond 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 clearly states it autofills an unsigned transaction with live network values (Sequence, Fee, LastLedgerSequence, NetworkID) for offline signing. It distinguishes itself from sibling tools like build_payment_unsigned by being a read-only preparation step, not a tx builder or signer.

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 tells when to use (to prepare tx for offline signing) and provides network selection guidance. It does not explicitly exclude alternatives, but the sibling list implies other tools for building or simulating transactions. The warning about mainnet vs testnet is helpful.

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