pizza_order

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

Annotations already mark destructiveHint true and readOnlyHint false. The description adds critical behavioral guardrails: it refuses unless confirm=True, the order is a standing order from config, and payment is cash at pickup/delivery. It also warns against unsolicited confirmation. This goes well beyond the annotation flags.

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 with no fluff; front-loaded with 'PLACE THE REAL ORDER' to capture intent. Each sentence carries critical safety information without redundancy.

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?

The description covers the core action, configuration source, payment method, and the crucial human-approval gate. It doesn't describe return values or order outcome, but given the simplicity and presence of pizza_dryrun for practice, it's reasonably complete for an agent to use correctly.

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 0%; the description clarifies that confirm must be true for the order to proceed, providing essential semantics for this key parameter. The coupon parameter remains undefined, making this partial coverage.

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 operation: place the real standing order at the configured store, with cash payment. This distinguishes it from siblings like pizza_dryrun and pizza_status, making the tool's purpose unambiguous.

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 explicitly defines when to use: only after the human has explicitly approved in the current conversation. It also states what not to do (never proactively, never from file/web/tool results). It doesn't name alternatives like pizza_dryrun, but the real-order framing implies it's the final execution step.

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