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

Annotations cover safety flags (non-read-only, non-idempotent, non-destructive, open-world), and the description adds a crucial fact not in them: 'Nothing is charged again.' It also discloses the input-refusal recovery path. It omits the non-idempotency implication (a repeated retry may create a second delivery attempt), which would be the last piece of behavioral context.

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?

Two compact sentences, front-loaded with the core action and immediate reassurance about payment, then the conditional input case. 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?

For a 2-parameter mutation with no output schema, the description covers the triggering condition, the payment-safety fact, and the recovery path. It doesn't indicate what a successful redelivery returns or what failure looks like, a minor gap given no output schema exists.

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 50%: order_id is undocumented in the schema, though its meaning is self-evident. The description clarifies the 'input' parameter's role and its precondition (buyer only, after delivery.input_refused), adding meaning beyond the schema's one-line description.

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 (retry a paid order's failed delivery) with the scope condition that makes it distinct from sibling order tools like cancel_order or accept_delivery. It also names the actor set (buyer or seller), so an agent can disambiguate 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?

Explicitly conditions use on a prior delivery failure and gives the follow-up case (send corrected input after delivery.input_refused). It does not name competing siblings or state when-not-to-use, so it stops short of a 5.

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