Best card for a store or category

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 states the output: the card, the honest rate, why, and caveats including merchant-code traps, activation, and ties. It also discloses what data sources are included and excluded. It does not describe the exact return envelope or edge-case behavior, but it provides substantial behavioral context for a query-style tool.

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 three tight sentences with zero filler. The core purpose is front-loaded in sentence one, return contents and caveats in sentence two, and exclusions in sentence three. Every sentence earns its place and nothing repeats schema content.

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 six parameters, nested objects, no output schema, and no annotations, the description covers purpose, returned contents, caveat types, and scope exclusions. The schema covers parameter formats and enums. The main gaps are that the exact response structure is unspecified and the conflict behavior when both merchant and category are supplied is left implicit, but the combined description and schema are sufficient for a competent agent.

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 six parameters including wallet, merchant/category, on, valuation, and chosen_categories. The description reinforces the merchant-vs-category idea and 'given cards' from wallet, but adds little semantic detail beyond what the schema provides. This matches the baseline-3 case where structured 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 opens with a concrete question: 'Which of the given cards earns the most at a store (merchant) or for a spend category, today.' It specifies the verb (compare/rank), the resource (given cards), and the scope (store or category). It also distinguishes itself from siblings like search_cards and lookup_merchant by focusing on selecting the best earn rate rather than retrieving card data or merchant metadata.

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 clearly bounds when the tool is valid: it only considers base rates, rotating bonuses, and built-in card benefits, and explicitly says personal bank offers are not consulted. This implicitly tells an agent not to use it when a user's personalized banking offers are in play. However, it never names sibling tools or states when to prefer them, so the guidance is strong on scope but not fully explicit on alternative routing.

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