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

Beyond the annotations, it discloses the pay-per-call model with exact prices and networks, that an unpaid call returns isError with a fresh x402 PaymentRequired invoiceId, that unpaid calls cost nothing, and that settlements are final with no refunds. It also describes the returned provenance fields (source_url, retrieved_at, calendar_version, attribution), which the agent could not infer from the schema or annotations.

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 opening clause repeats pricing already present in the title and the sentences are long and run-on, mixing payment mechanics, data provenance and legal disclaimers into one paragraph. The parenthetical that EU-T2 information 'is free on the ECB website' actively weakens the pitch and is arguably wasted text. Purpose is nevertheless recoverable early, so it is not disorganized, just overstuffed.

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 six-parameter paid tool with no output schema, the description covers the essentials: what is computed, which calendars and years, how the payment handshake and error path work, and what metadata accompanies results. Only minor gaps remain, such as behavior for dates outside the published calendar range or exact response shape for add_n.

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 baseline is 3; the description still adds meaning by explaining what each op produces (raw is_business_day/weekend/holiday readings, add_n step arithmetic, holidays_in_year lists with provenance) and by tying the year parameter to the 2026-2028 calendar window. It does not add format or range detail beyond what the schema already states for date/n.

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 names the resource precisely (civil-date business-day check over published US-FED, GB-EAW/SCT/NIR, SG, IE and EU-T2 holiday calendars for 2026-2028) and enumerates the three operations (is_business_day, add_n, holidays_in_year). An agent can tell exactly what the tool answers without opening the schema, though no sibling differentiation is offered.

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 frames the tool as solving one specific question, states the covered calendars and year window, and gives a clear boundary ('not legal, tax, filing or settlement advice'). It also gives operational guidance for the paid flow: omit payment_signature on the first call to receive payment requirements, then retry with a signed payload. It does not name alternatives, but no sibling appears to overlap this function.

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