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

The description reveals that the new limit fully replaces the old one, and that the tool can both raise and lower spending authority, which is important behavioral context. It also warns about SPEND_INTERVAL_YEARLY being rejected. The annotations already indicate idempotent and non-destructive, but the description adds specifics like 'replaces the old one outright' and the issuer rejection behavior.

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 compact yet information-dense. Each sentence earns its place: the core operation, the unit clarification with example, the replacement semantics, a never-round-up guardrail, and interval constraints. There is no fluff or repetition, making it appropriately sized and front-loaded.

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 has three parameters and an output schema, the description covers the essential invocation aspects: units, interval choices, replacement behavior, and an unsupported interval. It omits details like error handling or prerequisites, but these are likely covered by the output schema and openWorldHint. It is reasonably complete for the agent to select and invoke 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?

The schema is sparse (only cardId is described), so the description compensates by explaining that amount_cents is in cents with a concrete example, and by clarifying which interval enum values are supported vs. rejected, including a conversion instruction. It does not mention 'SPEND_INTERVAL_UNSPECIFIED' from the enum, but overall it adds strong value beyond the schema.

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 action: 'Replace a card's spend limit at the issuer.' This specific verb+resource combination distinguishes it from sibling card tools like card_freeze_card, card_unfreeze_card, and card_get_card_spend. The purpose is unambiguous and immediately understandable.

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 parameter guidance: which SPEND_INTERVAL values are acceptable (MONTHLY, DAILY, TRANSACTION), which is rejected (YEARLY), and how to convert a yearly figure to monthly. It also instructs to send the exact amount and never round up. However, it does not explicitly mention alternative tools or state when not to use this tool, so it falls short of a 5.

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