Delivery: create parcel [sandbox]

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

Annotations indicate it is not read-only (readOnlyHint=false) and not idempotent. The description adds that it has no real-world effect and is safe for testing, clarifying the sandbox nature. No contradiction with annotations.

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 a single paragraph that covers purpose, usage, and lifecycle context without unnecessary repetition. It is concise and front-loaded, though slightly verbose with the list of downstream tools.

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?

Considering the tool has no output schema but the description mentions the return value (parcelID), it is fairly complete. It also references related tools and the sandbox environment. Some details about optional parameters and their effects could be added, but overall adequate.

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 description adds minimal value. It mentions that 'tags' are for sandbox scenarios, but the schema already describes each parameter adequately. Baseline 3 is appropriate.

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 explicitly states it creates a test parcel in Sandbox with no real-world effect and returns a parcelID. It clearly distinguishes from the production tool delivery_create_parcel, and its role as an entry point for the sandbox lifecycle is well-defined.

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 specifies it is for sandbox testing for delivery-service partners, and contrasts with delivery_create_parcel (production). It also lists downstream tools that use the returned parcelID. While it doesn't explicitly state when not to use, the context is clear.

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