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

Annotations only declare the safety profile (not read-only, not destructive, closed-world), while the description adds genuinely new behavior: idempotency ('safe to call again: a completed purchase is returned as it is'), the pre-settlement failure contract ('fails with next_action'), and what the response contains. It stops short of 5 by not stating auth/ownership requirements for the purchase or what next_action implies operationally.

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 tight sentences, front-loaded with the precondition and then the idempotency/failure behavior, with no filler. The phrasing 'the add-on's entitlement on your DID-LLM until covers_until' is slightly awkward to parse but carries real 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 one-parameter, idempotent completion call with an output schema and clear annotations, the description covers trigger condition, idempotency, and failure mode — everything needed to invoke it correctly. Return-value detail is already carried by the output schema, so the description is adequately complete without it.

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 the single purchase_id is already documented in-schema with its pattern and its origin ('purchase_id from dmd_purchase'). The description adds no meaning about the parameter beyond what the schema provides, so the baseline 3 applies.

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?

The description states the concrete outcome of calling it — the DebitMyData-signed receipt plus the add-on entitlement on the DID-LLM until covers_until — which is more specific than the title alone. The action verb ('complete the purchase') is only implied by the name/title rather than restated, and no sibling tool is contrasted, so it falls short of a 5.

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?

It gives a clear precondition ('Once the add-on's payment is settled') and an explicit when-not ('Before settlement it fails with next_action'), which tells the agent both the right moment and the failure mode if called too early. It does not route to an alternative sibling (e.g. a payment-status or purchase tool) when the precondition is unmet, so the agent must infer that from 'next_action'.

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