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

Annotations are minimal (readOnlyHint=false, destructiveHint=false). The description adds that this creates a draft order, returns a checkout URL, and that the human handles payment. No contradictions with annotations. Provides useful behavioral context beyond what annotations convey.

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 pack essential information: purpose, inputs, outputs, and usage guidance. No redundant words, front-loaded with the key action.

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 zero parameters, the description explains the output format, mentions prerequisites (get_order_preview), and sets expectations (human pays). It is self-contained and provides a complete picture 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?

No parameters in schema, so baseline is 4. The description mentions 'cart + address + promo' as implicit context, which clarifies what state the tool uses, adding value beyond the empty schema.

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 uses a specific verb ('Create') and resource ('draft order'), and clearly states the inputs (cart, address, promo) and output format ({checkout_url, draft_id, expires_at}). It distinguishes itself from siblings by explaining the workflow (agent never pays, human opens URL).

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?

Explicitly instructs to call get_order_preview and confirm with the human first, and states 'The agent never pays,' which sets clear usage boundaries. However, it does not explicitly mention when not to use the tool or compare with siblings like checkout_link.

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