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

With no annotations, the description carries the full burden and does so well: it discloses supported corridors, payment method, return ranking by recipient amount, included fields, quote date/source, stored-quote behavior, live-quote behavior, and the caveat that the cheapest provider changes with amount. It also notes fresh mode is slower, and the schema adds the daily read limit.

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 front-loaded with the usage trigger, then moves through scope, return shape, freshness behavior, and the key caveat in five tight sentences. Every sentence adds information; there is no filler.

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?

There is no output schema, so the description must explain return values—and it does, listing ranking by recipient amount, provider fee, exchange rate, quote date, and source. It also covers freshness, supported corridors, payment rail, and amount sensitivity, leaving the definition complete enough to call 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 only 33%, so the description had to compensate: it explains that amount maps to the nearest stored quote ($200 or $1,000) unless fresh is true, and that only USD->MXN and USD->INR are supported today. It adds meaningful semantics beyond the bare schema, though it leaves some ambiguity about why the corridor enum lists many more options than are described as supported.

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 description states a specific verb and resource: comparing providers for sending US dollars abroad when the owner asks who is cheapest. It also separates itself from the sibling cheapest_way_to_get_paid by framing the direction as sending money abroad rather than getting paid.

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?

It gives a clear triggering condition ('When the owner wants to send US dollars abroad and asks who is cheapest') and explains when to use fresh: true ('when the owner is about to act on the number'). It does not explicitly name alternatives or when not to use it, so it falls short of a full 5.

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