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

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing the paid model ($0.001 USDC), the two-call 402 handshake, that failures are not charged, that an unknown currency returns 404 uncharged, and that the fiatdock-mcp package auto-pays. These are exactly the behavioral facts an agent cannot get from structured fields.

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 the critical facts (PAID, what it returns) and every clause carries information. The nested em-dash constructions make the single dense paragraph slightly harder to parse than it needs to be, but there is little waste.

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 an output schema present, return-value explanation is not required, yet the description still covers output shape, payment protocol, error/charge semantics, and currency coverage. An agent has everything needed to invoke it correctly, including the required two-step payment.

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 description coverage is 100%, so the schema already documents `to`, `from`, `amount`, and the payment envelope with defaults and limits. The description reinforces defaults and currency breadth but adds no syntax or format meaning beyond the schema, so the baseline 3 applies.

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+resource up front: 'Live exchange rates and a conversion,' and defines exactly what is returned (units of each target per unit of `from`, the converted amount, plus the ECB reference rate and deviation). It is immediately distinguishable from siblings like token_price or get_quote.

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?

Gives clear context for use (fiat+crypto conversion with an independent ECB cross-check) and a scope caveat ('Rates for information, not an executable quote'), which steers the agent away from treating it as a tradeable quote. It does not explicitly name a sibling alternative, so it falls short of the top band.

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