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

Annotations provide only openWorldHint and destructiveHint, so the description carries the transparency burden. It discloses important behaviors: creating a card moves no money but provisions a real instrument, the card cannot be deleted (only frozen), and the full card number/CVV are never returned. This is beyond what annotations convey and is essential for safe usage.

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 a dense paragraph but every sentence adds value. It is front-loaded with the main purpose and then covers required parameters, return fields, and critical warnings. While it could benefit from bullet points for readability, there is no fluff or repetition.

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 covers the required parameters, return fields, irreversibility, and retry policy, which is sufficient for a creation tool with an output schema. Some optional fields like zip, address, and provider are not mentioned, but they are not essential for basic use. The description provides enough context to invoke the tool correctly.

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 compensate. It thoroughly explains the key parameters: company_id (with membership verification and reference to get_my_companies), nickname (user-provided name), spend_limit_cents (in cents with concrete example), and spend_interval (required when limit is sent, with specific enum values and the yearly caveat). It also clarifies when to omit both fields.

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 begins with 'Issues a new virtual card at the card issuer,' using a specific verb and resource that clearly distinguishes this tool from sibling card tools like freeze, unfreeze, and update. It unambiguously states the tool's function.

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 tells the agent to pass a company the user belongs to (referencing get_my_companies), when to include or omit spend_limit_cents and spend_interval, which spend intervals to choose, and to avoid SPEND_INTERVAL_YEARLY. It also instructs to create one card per request and never retry a successful create.

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