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

Annotations already signal a dangerous, non-read-only, idempotent operation, but the description adds the critical context that real prepaid credit is spent, that authorization and budget approval are required, and that retries must reuse the same idempotencyKey. This goes well beyond the annotation flags and warns the agent of financial consequences.

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, no filler: core action first, then prerequisites, then retry/anti-pattern guidance. Every sentence earns its place and the most important safety information is front-loaded.

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?

The description covers the essential safety context (real credit, auth, budget, destructive nature) and the idempotency behavior for a two-parameter tool with no output schema. It is missing only minor niceties such as success/failure response details or what state the order transitions to, but nothing an agent needs to avoid a critical mistake is absent.

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?

With 0% schema description coverage, the description must compensate for the bare schema. It gives orderId meaning as the existing order being paid and idempotencyKey operational meaning as a token to reuse after timeouts—semantics the schema's pattern/length constraints cannot convey. It stops short of explaining the key's creation or what happens on failure, so not a 5.

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 opens with a specific verb phrase—'Spend real prepaid credit and initiate delivery for an existing order'—that names both the action and the resource. 'Existing order' explicitly differentiates it from create_order, and the rest of the sentence leaves no ambiguity about the tool's role.

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 states the authorization prerequisite (wallet:spend), the need for a user-approved budget, and gives concrete retry guidance: reuse idempotencyKey after timeouts and never create a replacement order. This tells an agent both when the tool is appropriate and which alternative (create_order) to avoid.

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