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

Goes well beyond the annotations by disclosing the preview/confirm/atomic semantics: 'previewed together, confirmed once by the merchant, applied all-or-nothing' and 'Changes nothing by itself.' The annotations only give safety flags; the description explains the human-in-the-loop and transactional behavior the agent needs to reason about.

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 core mechanic and followed by the use case and the key caveat. No filler or redundancy.

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 complex orchestration tool with no output schema, the description covers the essential mental model: composition, single confirmation, atomic application, and no side effects on its own. Minor gaps remain around step-count limits and what a preview returns, but nothing blocking.

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 0% for the top-level 'steps' property, but the description compensates by explaining that each step names a capability tool and supplies that tool's input. It does not surface the 2-item minimum / 8-item maximum constraints, so it is not fully compensating.

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 a specific verb (propose) and resource (a multi-step plan), and immediately distinguishes this meta-tool from the flat capability siblings by explaining it bundles several steps into one proposal. An agent can tell this is a composition/orchestration tool rather than a single mutation.

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 concrete trigger: 'Use when the merchant asks for one thing that takes several steps (a sale plus its coupon).' This implies when-not (single actions go straight to the capability tool) but never names the alternative explicitly or states the inverse condition outright.

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