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

Goes well past the annotations by disclosing the cost ($0.5 USDC on Base), the payment/auth model (Shelf Pass via pass_token or X-SHELF-PASS, only spent above the ≤$0.25 ceiling), and the exact failure mode (payment_required with the x402 v2 URL and header name). It even pre-empts a misread by stating the tool does not return a bare payment link in place of the rate. Annotation readOnlyHint=false is consistent with a call that spends credits.

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?

Front-loads what the tool returns, then cost, then auth behavior, then the payout/failure caveat. It is dense but each sentence carries information an agent needs (contents, scope, price, pass behavior, non-payment return), with 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?

With no output schema, the description correctly carries the return-shape burden: rows with source and time, plus the payment_required branch with the x402 URL. Combined with the priced/pass mechanics, an agent has everything needed to invoke it correctly and interpret both success and failure responses.

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 pass_token thoroughly; the description nonetheless adds value by naming the header alternative X-SHELF-PASS and the ceiling condition under which the token is not spent. That is a modest but real addition over the structured field.

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?

Names a specific verb (brief) and resource (Africa FX daily), then enumerates the exact contents: every Frankfurter official pair, both Bybit-derived street quotes (USD-NGN, USD-GHS), their spreads, and per-row source/time. This distinguishes it from the sibling get_fx_official and get_fx_parallel tools without the agent needing to open any schema.

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?

"One call for a morning pricing check" gives a clear usage context, and the surface area implies it consolidates the official and parallel partial views. It does not, however, explicitly state when to prefer it over get_fx_official or get_fx_parallel, so the routing guidance is implied rather than explicit.

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