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

With no annotations provided, the description carries the full burden of behavioral disclosure. It openly explains that `days` is a ceiling not a guarantee, that series start at different dates per currency, that `series_coverage` reports what is actually spanned, that market data is not ECB, that peg context includes third-currency pegs, and that errors name the missing leg. This is exceptionally transparent about edge cases and potential misinterpretations.

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 description is long but every sentence serves a purpose. It uses paragraphs, bolded warnings, and a clear separation between the main description, args, and examples. The structure makes important caveats prominent without being verbose or repetitive.

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?

Given the tool's complexity (source distinctions, data gaps, peg context) and the absence of annotations, this description is remarkably complete. It covers return values, error handling, historical coverage semantics, and user precautions. The presence of an output schema reduces the need to explain return structure, but the description still covers all important behavioral aspects, making it fully adequate for an agent to select and invoke the tool 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?

The schema provides no descriptions (0% coverage), so the description must compensate. It does so thoroughly in the Args section: base and target are defined as ISO 4217 codes, and days is explained as a lookback window with a default of 90 and a clear caveat that it is a ceiling, not a guarantee. The inclusion of examples further clarifies parameter usage.

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 clearly states the tool's purpose: 'Get the historical reference exchange-rate series for a currency pair.' It uses a specific verb ('Get'), identifies the resource ('historical reference exchange-rate series'), and distinguishes itself from the sibling 'fx_rate' tool by emphasizing 'historical'. This makes it unambiguous and differentiates it from other rate-related tools.

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 description provides explicit usage guidance, including that both currencies are required, there is no implicit EUR/USD default, and how to interpret `series_coverage` and `source` fields. It also gives strong when-not guidance (e.g., never describe a market series as ECB, never fill gaps from memory). However, it does not explicitly mention alternatives or when to use this tool versus sibling tools like `fx_rate` or `fx_volatility`, so it falls short of a 5.

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