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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so safety is covered. The description adds valuable behavioral context about the computation method (Pearson correlation of daily log-returns) and the banding logic, which goes beyond what annotations provide. It also specifies the base currency (USD), which is not in the schema. This enriches the agent's understanding without duplicating annotation data.

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, efficient and free of fluff. It front-loads the core function and then adds the output banding detail and use case. Every sentence contributes meaning, making it appropriately concise and structured.

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?

The description explains the purpose and output banding, but lacks details on the exact output structure (e.g., which currency pairs) and the meaning of parameters like basket and horizon_days. Since there is no output schema, the description should compensate but does not fully. It is adequate for a simple read-only tool but leaves gaps for an agent to correctly set parameters and interpret results.

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 0%, so the description must explain both parameters. The description mentions 'basket' but does not elaborate on its possible values (g10 vs majors) or their meaning. It completely omits the horizon_days parameter, leaving its role (lookback window) unclear. Without parameter descriptions in the schema or description, an agent cannot determine appropriate values or their impact on the output. The description adds no semantic value beyond the parameter names themselves.

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 computes 'Pearson correlation of daily log-returns vs USD across a basket' – a specific verb, resource, and scope. It also explains the output banding (strong_positive/positive/neutral/negative/strong_negative), making it distinct from other FX tools like fx_rates or fx_convert which focus on levels or conversions.

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 phrase 'Treasury/risk workflow for understanding multi-currency exposure' provides some context on when to use this tool, implying it is for correlation analysis rather than rate lookups. However, it does not explicitly contrast with sibling tools (e.g., fx_strength, fx_volatility_leaders) or state when not to use it. No alternative tool is named, leaving the agent to infer the differentiation.

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