get_historical_rates

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds useful context: it specifies the API key requirement (ALLRATES_API_KEY) and describes the data granularity for each period (e.g., hourly for 1d, daily for 7d/30d, weekly for 1y), which goes beyond the input schema. However, it does not cover other behavioral aspects such as rate limits, error handling, response format, or whether it's a read-only operation, leaving gaps for a tool with authentication needs.

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 appropriately sized with two sentences: the first states the purpose and period details, and the second specifies the API key requirement. It is front-loaded with key information and avoids unnecessary words, though it could be slightly more structured (e.g., separating period details into a list). Every sentence adds value, making it efficient but not perfectly optimized.

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 (3 parameters, authentication requirement, no output schema), the description is moderately complete. It covers the purpose, period options with granularity, and authentication need, but lacks details on output format, error cases, or sibling tool differentiation. Without annotations or an output schema, more behavioral context would be beneficial, but it meets a minimum viable level for basic understanding.

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 input schema has 100% description coverage, with clear documentation for source, target, and period parameters. The description adds minimal value beyond the schema: it mentions 'currency pair' which aligns with source/target, and lists the period options with data granularity details, but does not provide additional syntax, format, or usage examples. Given the high schema coverage, a baseline score of 3 is appropriate as the description compensates slightly but not significantly.

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 historical exchange-rate data points for a currency pair over a period.' It specifies the verb ('Get'), resource ('historical exchange-rate data points'), and scope ('currency pair over a period'), which distinguishes it from siblings like get_exchange_rate (likely current rates) and list_currencies (likely currency metadata). However, it doesn't explicitly differentiate from get_rates_authenticated, which might also provide historical data, leaving some ambiguity.

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 implied usage context by listing available periods (1d, 7d, 30d, 1y) and stating it requires an AllRatesToday API key, which suggests when to use it (for historical data with specific timeframes and authentication). However, it lacks explicit guidance on when to use this tool versus alternatives like get_rates_authenticated or get_exchange_rate, and does not mention any exclusions or prerequisites beyond the API key.

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