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 mentions the output categories (series and statistics, including min/max/avg/current/change) and the time range, which is useful. However, it does not specify the output structure, data granularity (e.g., daily vs monthly points), or any other behavioral details like pagination or error conditions, leaving some uncertainty about what the caller receives.

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 two sentences with zero waste. It front-loads the core purpose and follows with a single, relevant usage pointer. Every word earns its place, making it easy to parse quickly.

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 tool with three parameters and no output schema, the description explains the essential request semantics and points to a prerequisite tool. However, because there is no output schema, the description should more thoroughly describe the shape of the returned series or statistics. The current text is sufficient for making the call but not fully adequate for interpreting the result without additional assumptions.

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 description coverage is 100%, so the baseline is 3. The description adds value by mapping 'origin' to an exchange house and 'period' to months, which reinforces the schema. It also directs users to list_houses for valid origin IDs, going beyond the schema and genuinely helping the agent supply correct parameter values.

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 function: retrieving historical rate series and statistics (min/max/avg/current/change) for an exchange house and currency over a configurable number of months. It specifies the verb, resource, and key parameters, making its intent evident. However, it does not explicitly differentiate itself from sibling tools like get_rates or daily_summary, so it falls short of a perfect score.

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 clear context for when to use the tool: when historical rate series and statistics are needed over the last N months. It also gives a concrete prerequisite instruction, 'Use list_houses for valid origin ids,' which aids correct invocation. It does not mention exclusions or alternatives such as 'for current rates, use get_rates instead,' but the context is nonetheless clear.

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