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

Annotations only mark it read-only/open-world; the description adds substantial behavioral context beyond that: it is paid, it is not charged when no item can be answered, results come from a single dataset snapshot, and unpublished ranges resolve to unknown rather than an error. Those billing and failure-mode details are exactly what an agent needs before calling.

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 core question and the 1-50 pair scope, then layers constraints. It is dense and the single long final sentence packs several clauses, but each clause carries distinct information with 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 structure need not be explained, yet the description still summarizes per-item status, effective periods, rates with base units, source URLs, timestamps, and hashes. Combined with the billing and unknown-handling rules, an agent has everything needed to invoke it 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 100% and the nested item shape is documented in-schema, so the baseline is 3. The description does add the 2021-08-15 lower date bound and the base-unit (1 or 100) convention, but does not elaborate currency/date formatting beyond what the schema already states.

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 and resource: return Japan Customs' published JPY rates for a batch of 1-50 currency/date pairs. The batch scope, paid nature, and per-item ordered response distinguish it from the singular jp_customs_fx sibling without needing to open either 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?

Gives real boundary conditions: valid dates from 2021-08-15, unpublished periods and unlisted currencies return unknown, and it explicitly rules out date selection, tax calculation, market/remittance rates, and forecasts. It does not, however, name an alternative tool for single-pair lookups or other rate sources.

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