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

Annotations already cover the safety profile (readOnly, non-destructive, idempotent), and the description adds meaningful context beyond them: the output is an *unsigned* transaction the wallet must still sign, and lent stock only comes back 'once it is returned', which is a real availability caveat. It stops short of describing the transaction payload, fees, or any prerequisite approvals.

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 core action and the all: true switch, with no filler. The trailing sentence about stock returning 'once it is returned' is slightly cryptic in phrasing but earns its place as a timing caveat.

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?

With no output schema, the description should say what the caller receives (an unsigned tx object to sign) and what happens if neither amount nor all is supplied, since only wallet and asset are required. The prepare-then-sign flow is hinted at but not fully spelled out, leaving a meaningful gap for a transaction-building tool.

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 100%, so the baseline is 3, but the description genuinely adds semantics: it clarifies the either/or between taking 'part' (amount) and 'all with all: true', a mutual-exclusivity the schema does not express. It leaves the exact amount format to the schema, which is appropriate.

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?

States a specific verb and resource: builds an 'unsigned transaction to take back lent stock or USDG', which is a concrete action an agent can match to intent. It implicitly distinguishes itself from siblings like borrow, supply, and withdraw_cover by scoping to returning lent assets, but it never names an alternative to contrast against.

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?

Usage is implied by 'take back lent stock or USDG' and the either/or of a partial amount versus all: true, so an agent can infer when it applies. However, there is no explicit when-to-use/when-not guidance relative to siblings such as release_collateral, withdraw_cover, or farm_withdraw, which are close enough in name to cause confusion.

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