Quote a send without gas

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

Goes well beyond the annotations: quote is free, valid 10 minutes, nothing moves on-chain until signing, and it enumerates failure modes with limits ($2–$1,000, Tron from $10, insufficient balance, frozen token, 10 transfers/24h). It even returns a status of 'quoted', reinforcing the non-mutating nature. The annotations say readOnlyHint=false and destructiveHint=false, which is consistent (a quote creates state but destroys nothing), though the description could have explicitly reconciled that a quote is a write-shaped but safe call.

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?

Dense but front-loaded: purpose first, alternative second, then return shape, workflow, and error conditions. The long final sentence packs several failure modes together but each clause is actionable. Slightly heavy, yet nearly every sentence carries operational information.

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 supplies the return shape ({ summary, transfer }) and the status value, plus the approval workflow and the error envelope. For a quoting tool that gates a real transaction, that covers everything an agent needs to call it and handle the result.

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 schema already documents chain, token, amount, sender and recipient with formats and examples. The description adds only domain-level semantics — fees come out of the amount, token/chain availability comes from gasrescue_info, amount bounds — but does not restate parameter-level syntax. Baseline 3 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 — pricing a gasless stablecoin send — with concrete tokens (USDC/USDT/USDG), the absence of native gas, and example use cases (exchange deposit, another wallet). It explicitly names the sibling quote_swap and the condition that selects it, so the agent can discriminate without opening schemas.

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?

Explicit routing: 'Use quote_swap instead when the user wants gas in the same wallet.' It also gives the downstream workflow (show summary, get approval, then sign) and the fleet of failure conditions that mean the call will not work, which is when-to-use guidance at its strongest.

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