pizzahut_delivery_estimate

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

With no annotations, the description carries the full behavioral burden and excels. It explicitly states the tool is read-only (no cart, order, payment, or account info), explains the semantics of the 'serviceable' field (true only when upstream returns a real estimate, false with reason for other cases), and discloses the caveat for the INTERNAL provider regarding deliverable radius. It also explains why order_subtotal is required and the default for pickup_at. This is comprehensive transparency.

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 relatively long but every sentence adds substantive information. It is front-loaded with the core purpose, then details caveats and parameter rationale. There is minimal redundancy. It could be slightly trimmed, but the structure is logical and each point earns its place, such as clarifying the read-only nature and the serviceable semantics.

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's complexity (12 params, 8 required, no output schema), the description covers key behavioral aspects: read-only, serviceable semantics, caveats, and parameter defaults. It mentions the response includes serviceable, fee breakdown, and pickup/dropoff time, giving the agent an idea of the output. It references additional documentation for a specific caveat. It could be more explicit about the expected response structure, but overall it provides enough for correct invocation.

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 covers 100% of parameters with descriptions, giving a baseline of 3. The description adds meaning beyond the schema by explaining that order_subtotal materially affects the fee estimate and is therefore required, and that pickup_at defaults to 30 minutes from now. This provides rationale for parameter usage not present in the schema. While other parameters are adequately described in the schema, the description adds value for two key ones.

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 tool's function: checking Pizza Hut delivery serviceability and estimated fee for a given store and address. It specifies the verb 'check', the resource (serviceability and fee), and distinguishes itself from ordering tools by noting it does not place orders or take payment. It also differentiates from similar tools like kfc_delivery_estimate by focusing on Pizza Hut.

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 clear context for when to use the tool: to obtain a delivery estimate without placing an order. It implies usage for read-only checks and mentions it reads the same estimate as Pizza Hut's site. However, it does not explicitly name alternative tools or provide explicit exclusions, such as 'use this only when you need a delivery estimate, not to place an order'. The distinction from ordering tools is implied but not stated as a direct alternative.

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