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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, so the bar is lower; the description still adds genuinely useful behavior: the call records approval only and does not move funds. It omits whether a failed or duplicate release is rejected, and says nothing about what the confirm/terms proof guarantees.

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 sentences, zero filler, with the confirmation action front-loaded and the critical non-effect (does not pay the processor) placed where it will be read before invocation.

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 6-parameter mutation with five required fields and no output schema, the description covers intent and the not-a-payment caveat but leaves the majority of required inputs semantically undefined. An agent can tell why to call it, but not confidently construct terms_sha256 or payment.

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 description coverage is only 33% — id and token are documented, but name, payment, terms_sha256 and confirm are bare. terms_sha256 in particular is opaque (a 64-hex digest of what terms?) and the description never explains what must be hashed or why the release requires it, nor what the 'payment' string should contain.

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 pairs a specific verb (records approval / confirms a payment condition) with the resource and explicitly bounds scope by excluding processor payment: 'This records approval; it does not pay the processor.' It distinguishes itself from settlement tooling but does not name or differentiate from near siblings like accept_offer or submit_purchase_order.

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 a real precondition — 'only where the inspected order allows the customer to release it' — which routes the agent to an inspection step (inspect_offer/inspect_delivery) before calling. There is no explicit when-not guidance or named alternative, 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.