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

Annotations already declare readOnly, idempotent, non-destructive, non-open-world. The description adds real behavioral detail beyond them: only orders on the linked account are found, other numbers produce a not-found error, and it previews what is returned at each fulfilment stage. It stops short of exhaustive disclosure (no rate limits or pagination notes), but this is well above the annotation baseline.

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?

Front-loaded with the trigger and the identifier format, then the return contents, then the sibling redirect. The second sentence is long and clause-heavy, but nearly every clause conveys actionable information.

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 single-parameter read tool with an output schema (so return fields need not be enumerated) and full annotation coverage, the description covers trigger, identifier format, auth scope, error behavior, and the start_return linkage. Nothing an agent needs to select or call it 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% and only one parameter exists, but the description still adds meaning: where the number comes from (my_orders or the confirmation email) and that a leading '#' is accepted. That is more than the schema's bare format hint.

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 and resource ('track ... order') and scopes it to teas.co.uk orders for a signed-in customer. It is clearly distinguishable from siblings like my_orders and start_return, which it explicitly names.

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?

Gives an explicit trigger ('when a signed in customer asks where their order is') and routes to the correct alternative ('For a list of recent orders use my_orders'). It also states a precondition (only linked-account orders resolve) and the failure mode for anything else.

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