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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds real behavior: it takes no input, requires a linked/signed-in account, returns an error otherwise, and that zero points is a normal answer for a new account. The enumeration of return fields is somewhat redundant given the output schema exists, which keeps this from a 5.

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 usage trigger, then return/behavior details, then sibling routing – every sentence carries information. It runs slightly long with four clauses in the final sentence, but nothing is filler.

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 zero-input, read-only lookup with an output schema, the description covers everything an agent needs: the trigger condition, the auth prerequisite and its error case, the normalcy of zero, and where to go for redemption or order history.

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?

Zero parameters, so the baseline is 4; the description explicitly states 'It takes no input,' confirming the empty schema. No further parameter meaning is possible or needed.

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?

Starts with a specific trigger ('when a signed in customer asks how many teas.co.uk reward points they have or what they are worth') and states exactly what is returned. It is immediately distinguishable from siblings like my_orders and checkout_link, which it names and delimits against.

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 explicit when-to-use (signed-in customer asking about points/balance) and explicit when-not (cannot redeem points), routing redemption to checkout_link and order history to my_orders. No inference is required to pick this tool over its siblings.

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