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

Beyond readOnlyHint and openWorldHint, the description discloses the data provenance (KyberSwap, ParaSwap, Jupiter, Across, Circle CCTP, LI.FI), keyless access, that every figure carries a source, time and Rate Receipt, that failures retain their reason, that figures are never ranked, and the free daily allowance. It also states the no-custody and no-signature posture and the access_key gating of venue names, which are meaningful behavioral facts the annotations do not carry.

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 core purpose is front-loaded, but the body is a single sprawling paragraph mixing purpose, data sources, fee models, hourly reads, destination behavior, guarantees and billing, several of it in fragment form ('The hourly reads at USD 10k, 100k, 1m and 5m for the pair, each with its age'). Much of it earns its place, yet the lack of structure makes the tool harder to scan than it needs to be.

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 carries the full burden of describing returns, and it does: executable depth and cost, price impact against a USD 100 quote, per-chain fee models with 24-hour ranges, bridge cost and time, hourly reads with age, and destination facts with explicit 'not established' handling. Failure handling and receipt provenance are also covered, leaving nothing an agent needs in order to call it correctly.

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 all six parameters; the description's contribution is marginal but real. It adds conditional meaning for destination (triggers supplier acceptance facts and off-ramp venue reads), for access_key (venue names appear only when a router key is present), and confirms the ZAR/NGN to ZARP/cNGN mapping.

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 clause states a specific verb and resource: finding where a stablecoin payment of a given size can be filled on-chain and at what cost, and it enumerates the exact outputs (depth, price impact, network fees, bridge cost, hourly reads, destination facts). It never names a sibling such as check_provider_liquidity, liquidity_map or swapeazi_dex_cost, so differentiation from those tools is left to the agent, but the resource itself is unambiguous.

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 only implied through parameter conditionals: 'With destination (two-letter country), the documented facts on whether suppliers there take stablecoins directly' tells the agent when to supply destination, and the access_key note explains what enabling it changes. There is no explicit statement of when to choose this over check_provider_liquidity, swapeazi_dex_cost or get_corridor_rates, and no exclusions or prerequisites beyond 'Free within the daily allowance'.

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