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

Annotations already indicate destructiveHint=true and readOnlyHint=false; the description adds valuable destructive semantics: TagList 'fully replaces existing tags,' ShippingDetails 'replaces all existing packages,' and AppendMode toggles append vs replace. It also discloses the per-row Status enum values. No contradictions 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 dense paragraph that front-loads the core purpose. It efficiently lists key fields and behaviors, though the [DEMO] suffix is noise and the structure could benefit from bullet points for readability. It earns its length for a complex tool.

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?

For a complex mutation tool, the description covers all major capabilities, replacement behaviors, and the correct alternative for insurance type. The schema provides full parameter details and an output schema exists, so the lack of return-value discussion is acceptable. It could mention that Orders is an array and TxnId is required, but these are visible in the schema.

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%, so the schema already documents parameters in detail. The description contributes a high-level field summary (top-level, sub-objects) and adds the per-row Status enum values, which are not present in the input schema. This goes beyond simple repetition, though most details are mirrored in the 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 opens with 'Update existing orders in Teapplix'—a clear verb+resource pair. It distinguishes from siblings by listing specific updatable fields and explicitly routing InsuranceType to setOrderShipOptions, differentiating from related tools like create_order and manage_* tools.

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 an explicit alternative: 'For InsuranceType use setOrderShipOptions.' It also implies when to use this tool (for order-level updates including payment status, address, items, tags, queue, warehouse, memos, shipping details) but does not explicitly enumerate exclusions such as tag-only updates using manage_order_tags. This is clear context with one explicit alternative, but not comprehensive.

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