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

Beyond the readOnly/idempotent annotations, the description discloses genuinely non-obvious contract terms: no liquidation, no early close on price movement, unwind of the position on non-repayment with no further recourse, and a five-minute signing window for the wallet. It also compensates for the absent output schema by naming what is quoted — what the wallet receives and repays, cost, and loan-to-value — and explicitly states it signs nothing.

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?

Purpose is front-loaded and no clause is pure filler, but the whole definition is one ~90-word run-on sentence stitched together with colons, which makes the loan mechanics and the output description hard to parse on a first read. Splitting it into distinct statements — mechanics, quote contents, expiry, and no-signing — would lose nothing and read far faster.

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?

For a read-only quote tool with no output schema, the description covers the essential surface: collateral type and venues, the no-liquidation guarantee, the five-minute signature expiry, the fields returned, and the handoff to gage_prepare_lp_borrow. What is missing is failure context — what happens when the wallet lacks the position, the term is unsupported, or no vault can fund the loan whole — which is left implicitly to gage_capabilities.

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 adapter, tokenId, wallet, term, and vault are already fully documented in the schema, including the venue list and the omitted-vault default. The description adds no syntax, format, or constraint detail about these parameters beyond echoing the supported venues and referencing the wallet as quote signer. Baseline 3 applies where the schema carries the semantic load.

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 first clause states a specific resource — 'a quote for a fixed-cost USDG loan against an ETH/USDG or stock/USDG liquidity position' — and enumerates the supported venues, so an agent can tell it apart from gage_borrow_quote or gage_leverage_quote by the LP-collateral scope. It never names those siblings explicitly, so the differentiation must be inferred from the phrase 'liquidity position' rather than stated.

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?

Sequencing is only implied: the phrase 'with a prepare object for gage_prepare_lp_borrow' hints that this quote feeds the prepare step, and 'Signs nothing' tells the agent no wallet interaction happens here. There is no explicit statement of when to call this versus gage_borrow_quote or gage_leverage_quote, and no prerequisites such as needing the position to already be listed by gage_lp_positions.

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