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

Goes well beyond the annotations. Annotations declare a non-read-only, idempotent, non-destructive write; the description explains why it is idempotent (one rating per order, repeats return the existing one) and discloses the two-phase confirmation behavior where the first call returns scores but submits nothing. That is exactly the extra behavioral context a mutation tool needs.

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?

Three tight sentences, front-loaded with the action and its eligibility constraint, then the rating fields, then the idempotency and confirmation rules. No 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?

With no output schema, the description carries the return-behavior burden and does so for the confirmation case (first call returns the scores). For a 9-parameter mutation tool it is nearly complete, though the identifier parameters (orderId vs orderCode vs restaurantId) are left to 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 only 44%, and the description helpfully compensates for the undocumented fields: it defines food/deliverySpeed/packaging as 1-5 scores, comment as optional and short, riderRating as optional, and explains what confirmed: true does. It does not clarify the relationship between orderId, orderCode and restaurantId, which the schema partially 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 (rate) and resource (an order), plus the qualifying constraints: it must be the connected person's own and must be DELIVERED. It also enumerates the rated dimensions, so an agent can distinguish this from sibling tools like track_order or confirm_delivery_order without opening the 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?

Gives clear operative context: one rating per order, a repeat returns the existing one, and the confirm-each-decision flow requires a follow-up call with confirmed: true. It does not name an alternative tool or an explicit when-not-to-use condition, but no sibling overlaps this action.

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