pizzahut_bundle_choices

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

No annotations are provided, so the description carries the behavioral burden. It discloses that it 'Returns' a full choice-builder tree, that variants carry a 'real price delta' over the base price, that zero means covered and positive means upgrade. It also indicates the input provenance: bundle_code comes from /pizzahut/menu's code field on a type=bundle item. This is useful behavioral context beyond the schema.

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 well-structured, front-loading the core action, then adding examples, pricing semantics, sibling distinction, and the bundle_code source. It has a bit of repetition ('full choice-builder tree' appears twice) but remains readable and efficient for the necessary context.

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?

Because there is no output schema and no annotations, the description covers return semantics (named slots, variants, price deltas, zero or positive pricing) and parameter source. It could mention storage or what to call next, but for a bundle-tree tool, the description is thorough enough to guide a caller.

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 100% for the parameters, so the schema already documents each one. Still, the description adds meaning by explaining the bundle_code field's source and type (from /pizzahut/menu's code field on a type=bundle item), and the channel parameter relates to 'Order channel the deal and pricing reflect.' Together this is what an agent needs to provide the right values.

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 states a specific verb and resource: 'Get one Pizza Hut deal/combo's full choice-builder tree.' It is repeated once, but the first sentence plus examples ('1st Pizza', 'Wings or Fries', '1st Dip') make clear what slots and variants are returned. It explicitly contrasts with /pizzahut/modifiers to distinguish the tool from a sibling, so an agent can tell them apart.

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 says it is a different structure from /pizzahut/modifiers and explains that this endpoint swaps whole product variants in a combo, while the other customizes toppings/sauces on one product variant. This helps an agent decide which to use, though it does not give explicit when-not-to-use conditions or alternative names in a concise list.

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