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 does this well: it explains the asynchronous processing via a retrieval queue, the difference between U.S. and international card handling, the manual admin update for international cards, rate limits, and the 409 conflict behavior. This is rich behavioral context beyond what the schema provides. It doesn't mention side effects like whether the refresh mutates stored data, but the async and rate-limit details are substantial.

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: a one-line summary followed by two paragraphs of behavioral detail. It's front-loaded with the core action. The length is justified by the genuinely important behavioral differences (U.S. vs international, rate limits, 409). Every sentence adds value. It could be slightly tighter, but the structure is clear and scannable.

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 no output schema and no annotations, the description covers the key operational details: what happens for each card type, rate limits, conflict behavior, and the async nature. It doesn't explain what the response looks like (no output schema), but the description's behavioral detail compensates. The main gap is not stating what the return value indicates (e.g., success vs. pending), but overall it's quite complete for an async trigger tool.

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 schema already documents all three parameters. The description adds context about card_type behavior (U.S. vs international) which maps to the card_type parameter, and the rate-limit/409 behavior relates to card_id. However, the description doesn't add much detail about the auth_token parameter beyond what the schema says. Baseline 3 is appropriate since the schema does the heavy lifting.

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 states a specific verb ('refresh'), a resource ('card data'), and the core action ('Requests an updated balance for a card'). It clearly distinguishes this from sibling tools like get_card_data (read current data) and fund_card_balance (add funds). The first sentence is a clear, specific statement of what the tool does.

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 on when to use the tool: when an updated balance is needed. It also gives important usage constraints: rate limits (one request per 5 minutes, max 12 per 24 hours) and the 409 behavior when a refresh is already pending. However, it doesn't explicitly name alternative tools or state when NOT to use this tool (e.g., 'use get_card_data if you just need current data'). The usage context is strong but lacks explicit exclusions.

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