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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: account-scoped lookup that returns a not-found error for other numbers, courier tracking links once shipped vs a dispatch-time note before shipping, and the meaning of can_return as a downstream gate for start_return. This is exactly the behavioral context annotations cannot express.

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?

Five short sentences, front-loaded with the usage trigger and closing with the alternative tool. Every sentence carries non-redundant information (format, scope, shipped/unshipped behavior, can_return), and none restates the title or name.

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?

Despite an output schema existing, the description adds the differential response behavior (tracking links vs dispatch note) and the cross-tool can_return signal, so nothing an agent needs to call and interpret this correctly is missing.

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 baseline is 3, but the description adds genuine meaning the schema lacks: the number can come from my_orders or the confirmation email and may carry a leading '#'. It stops short of covering the 1-40 length bound, which the schema already handles.

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?

States a specific verb+resource ('track' a single teas.co.uk order) and immediately scopes it to one order for a signed-in customer, which cleanly separates it from the sibling my_orders that handles lists. An agent can distinguish it from start_return and my_orders without opening any schema.

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?

'Use this when a signed in customer asks where one teas.co.uk order is' gives the trigger condition, and 'For a list of recent orders use my_orders' names the alternative and the condition that selects it. The can_return mention also routes to start_return, covering the third closely-related sibling.

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