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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false), so the description's job is to add what they don't say. It does: it names the return payload (session id, cart, total) in the absence of an output schema, and it discloses the side effect that a sandbox API key is minted when none is supplied. It stops short of warning that a second call creates a new session rather than resuming one.

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 short sentences, front-loaded with the action and inputs, then returns, then the conditional api_key behavior. Nothing is padding.

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?

With no output schema, the description usefully summarizes the return values, and annotations carry the mutation safety profile. The remaining gap is lifecycle context — whether the session must be subsequently completed or can be abandoned, and whether repeated calls duplicate sessions.

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 100%, so all three parameters are already documented in the schema, including that product_id comes from list_products and what api_key means. The description's mention of products, quantities, and the api_key fallback largely restates that; 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?

States a specific verb and resource ('Start a checkout') and expands the concept into 'Agentic Commerce Protocol checkout session' with the inputs it takes and values it returns. It doesn't explicitly contrast itself with siblings like get_checkout or complete_checkout, but the create-vs-read-vs-complete split is self-evident from the resource framing.

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?

The description implies the usage context ('with the products and quantities the user wants') but never states when to prefer this over alternatives or what prerequisite state is needed. There is no explicit 'call get_checkout to poll' or 'then call complete_checkout' routing, so the agent must infer the lifecycle from sibling names.

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