prepare_safe_tx_propose

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

Annotations already indicate destructive and idempotent hints. The description adds significant context beyond annotations: it explains the approveHash flow, the EIP-712 hash computation, and that DELEGATECALL is flagged. There is no contradiction 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?

The description is dense but well-structured: purpose, inner modes, flow steps, and security considerations. Every sentence adds value, though it could be slightly more concise by omitting the Parenthetical 'recommended; pulls to/value/data from server-side state' which is clear from context.

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 no output schema, the description explains the return type (UnsignedTx for approveHash) and subsequent steps. It lacks mention of error conditions or prerequisites, but for a complex multi-step tool, it provides a good overall picture. The description is fairly complete for a tool with rich annotations and clear place in the workflow.

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 0%, so the description must compensate. It explains the 'inner' parameter's two variants (handle vs raw to/value/data) and mentions the operation enum with default and DELEGATECALL flag. However, it does not explain 'signer', 'safeAddress', 'chain' (enum values), or 'nonceOverride'. These are left to the schema, which lacks descriptions.

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 explicitly states 'Propose a new Safe (Gnosis Safe) multisig transaction' and distinguishes two modes (handle from prior prepare_* vs raw to/value/data). It clearly differentiates from sibling tools like prepare_safe_tx_approve and prepare_safe_tx_execute.

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 provides step-by-step guidance: recommends using a handle from a previous prepare_*, then broadcasting the returned UnsignedTx via send_transaction, then calling submit_safe_tx_signature. It also contrasts with the off-chain eth_signTypedData_v4 flow and explains why the on-chain approveHash flow is used. It flags DELEGATECALL as high-risk.

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