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 adds context about the data source being 'an open public exchange rate feed suitable for informational use,' implying limitations for auditable purposes. It also explicitly states it does not support cryptocurrency pairs. However, it does not detail error behavior, rate limits, or the exact rate type (mid-market), but the core behavioral traits are transparent.

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 well-structured and front-loaded with the main action, followed by usage alternatives and exclusions. It is slightly verbose with multiple 'Prefer' statements, but each sentence carries meaningful information and justifies its place. It is appropriately sized for the complexity of the tool and its sibling context.

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 simple nature (3 params, no output schema, no annotations), the description is highly complete. It states what the tool returns (converted amount and rate), when to use it, when not to use it, and the underlying data source limitations. It also covers the sibling-tool landscape, making the decision context clear.

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 does not add additional parameter-specific details beyond what the schema already provides (e.g., positive number, ISO codes, case-insensitivity). No extra meaning is needed, but the description also doesn't enhance the semantics further.

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: 'Converts a monetary amount between two fiat currencies using live exchange rates from an open currency exchange API. Returns the converted amount and the rate applied.' It uses a specific verb (converts) and resource (monetary amount between fiat currencies) and distinguishes from siblings by describing itself as an alternative live-rate source.

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 when-to-use and when-not-to-use guidance. It says 'Use currency_convert_open as an alternative live-rate source when currency_convert (Frankfurter/ECB) or currency_fx_lite are unavailable or rate-limited.' It also names preferred alternatives for different scenarios (accounting/compliance, minimal output, lightweight conversions) and excludes crypto pairs, pointing to crypto_fx_rates.

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