Card Changes

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), so the description is not obligated to restate it. Instead it adds genuinely useful behavior: results are 'verified' and ordered 'most recent first', and each event is a diff between two confirmed snapshots, which tells the agent the data model and that entries represent changes rather than current values. It does not mention pagination or coverage limits, keeping it at 4.

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?

Two dense sentences with no filler; the core purpose is front-loaded and the diff semantics are appended as a clarifying second sentence. Every clause carries information.

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?

An output schema exists, so return values need not be explained, and the description supplies the ordering and diff semantics that matter most for interpreting results. The only gap is the unexplained 'limit' parameter, which is minor given the output schema covers shape.

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 coverage is only 50%: 'sinceDays' is documented in the schema, but 'limit' has no description beyond its min/max bounds. The description mentions 'recent' but adds no meaning about how limit or sinceDays behave, so it fails to compensate for the uncovered parameter.

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 names a specific verb and resource ('Return recent verified credit-card fee and APR changes'), which is clearly distinct from siblings like get_card_offers or get_rate_freshness. It further sharpens the purpose by defining each event as a diff between two confirmed snapshots, so an agent knows this is a change-feed rather than an offer or rate listing. It stops short of explicitly naming the sibling it displaces, so 4 rather than 5.

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?

There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. 'Recent' hints at a recency use case, but the agent must infer when to pick this over get_card_offers, get_rate_freshness, or the rate/offer siblings. No prerequisites or exclusions are stated.

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