Card Downgrade Path

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the safety profile is fully covered elsewhere. The description adds the useful qualifier 'verified' (curated data, not raw scrape) and clarifies that the refund window is tied to when the annual fee posts. It says nothing about freshness, pagination, or auth needs, so this is adequate but not rich.

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 sentences, front-loaded with the return payload and followed by the optional filter. The parenthetical expansion of 'product-change' earns its place by disambiguating the term, and there is no filler.

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?

With an output schema present, the return shape needn't be described, and the tool has only one optional parameter whose schema is complete. The definition covers what is returned, the default behavior when the filter is omitted, and the data's verified nature – nothing an agent needs to call it correctly is missing.

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% and the single cardId parameter is fully documented in the schema, including the issuer:slug format and examples. The description's mention of the same filter and the omit-to-return-all behavior largely restates the schema, so the baseline of 3 applies.

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 uses a specific verb (Return) plus a precisely scoped resource: verified credit-card product-change (downgrade) paths and the issuer's fee-refund window. It even defines the concept inline ('which no-fee or lower-fee card a given card can be product-changed to'), so an agent knows exactly what it gets. It never names the adjacent siblings (get_card_changes, get_card_offers), so it stops short of explicit differentiation.

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 second sentence gives filtering guidance ('Optionally filtered to one card id... returns every verified path and window when omitted'), which tells the agent how to scope the call. However, there is no tool-level when-to-use versus alternatives, and no indication of when get_card_changes would be the better choice.

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