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

Beyond readOnlyHint/openWorldHint, the description adds genuine behavioral context: no point spend, no URL input, and a named failure mode — privacy_consent_required is returned once fields are supplied until the controller accepts the current privacy version, with the warning 'Do not invent that acceptance.' That is meaningful error-path disclosure for a read tool. It does not cover rate limits, caching/staleness of the daily rate, or which day's fix is returned.

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?

Four short sentences, front-loaded with the core purpose before the negative scope and the consent caveat. Each sentence carries distinct information with no filler; 'does not accept a URL' is slightly idiosyncratic but still useful hub-specific context.

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?

For a two-parameter lookup with no output schema, the description covers purpose, exclusions, cost, and the consent gate, which is reasonable. However, it leaves the two parameters undefined and gives no hint about what a successful result contains (rate value, reference date), which matters for an FX lookup whose whole value is the dated rate.

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 0% for both required parameters (base, quote), so the description carries the full burden — and it does not. It never explains that base/quote are ISO 4217 three-letter codes, which is the base currency and which the quote, or how the pair relates to the stated 'euro' reference rate. Only the word 'one' hints that a single pair per call is returned.

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 gives a specific verb+resource+scope: 'Look up one daily euro foreign-exchange reference rate.' It also draws contrast boundaries against sibling tools by ruling out a live trading quote, a payment rate, and a precious-metal price (i.e. hub_metals). It stops short of naming the closest sibling, hub_fx-backup, so it is clear but not maximally differentiating.

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?

The exclusions ('not a live trading quote, not a payment rate, not a precious-metal price') function as real when-not-to-use guidance and correctly route agents away from hub_metals and any trading-quote expectation. There is no explicit when-to-use statement or pointer to the backup sibling when this fails, so it is context-rich but not complete routing guidance.

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