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

Beyond the annotations, it discloses that the tool returns an unsigned base64 transaction, returns a pre-borrow health factor, requires x402 payment past the free tier, verifies the borrowed token instead of silently borrowing, and explains idempotency and two-phase execution. This is far more behavioral detail than the annotations provide.

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 long but the length is justified by the complexity of the operation. The core action and return value are front-loaded, followed by risk relevant warnings, idempotency semantics, and the two-phase execution flow. A few references to lend_deposit are repeated, but they support the same message rather than adding clutter.

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 critical execution context: collateral first, return behavior, payment requirements, token verification, idempotency, and the signed_transaction two-phase path. It does not explain several optional parameters directly, but given the already existing output schema and annotations, the remaining gaps are minor.

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 0% description coverage, so the description must carry parameter semantics. It covers amount, allow_unverified, payment_header, idempotency_key, and signed_transaction/verify well, but it remains silent on protocol, market, marginfi_account, caller_id, and pay_in_crank, leaving notable gaps in a 14-parameter tool.

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 opening sentence "Borrow against deposited collateral (non-custodial)" names a specific action and resource, and the rest makes clear this tool creates a borrow position, not a deposit or repayment. It is easily distinguished from siblings like lend_deposit and lend_repay.

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 context for when the action is possible ("Deposit collateral first"), notes when a payment header is required, and points to lend_deposit for the two-phase execution pattern. It does not explicitly list exclusions or contrast it with alternatives, but the usage flow is implied strongly enough.

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