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

With no annotations present, the description carries the full load and does well: it enumerates the exact return contents (edge dates, print count, years, ten oldest/newest prints, sha256 checksum) and discloses the commercial tiers and their per-call limits. Gaps remain around whether the preview is always free for any currency pair, whether it requires auth, and what 'print' means, but the behavior disclosed is substantially richer than typical.

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 free-tier payoff is front-loaded, which is good, but the second half collapses into semicolon-separated pricing fragments ('1,825 /series prints per call and 3,650 /series prints per call') that are ambiguous and hard to map to tiers. Pricing detail crowds out a plain statement of when to call this tool, so the sentence count is not fully earned.

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?

There is no output schema and no annotations, yet the description compensates well by itemizing exactly what the response contains, which is the key missing structure. For a two-parameter read probe this is close to sufficient; only the meaning of 'print', access requirements, and the relationship between the pair arguments and the returned checksum are left open.

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 both from/to parameters carry their own defaults and descriptions, so the schema does the heavy lifting. The description adds only indirect meaning by labeling the data as FX and implying a base/quote pair; it says nothing about accepted codes, fallbacks, or how the pair affects the checksum. 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?

The description states a specific resource and scope: a free preview of FX series history depth, returning first/last date, print count, years covered, and edge prints. It is clearly a metadata/coverage probe rather than the data itself, which distinguishes it from the paid series retrieval it references. It never names the sibling tool it complements (e.g. indonesia_series) by name, so differentiation is by implication rather than explicit routing.

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 free-versus-paid split gives an implicit when-to-use signal: take this preview to judge coverage before paying. However, it reports tier prices and per-call print limits rather than telling the agent when to choose this tool over indonesia_series, indonesia_data_preview, or indonesia_coverage_report. There are no explicit exclusions or prerequisites such as what a 'licence holder' status requires.

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