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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile requires no description support. The description does add the return content (status values open/paid/unpaid/expired plus amount and payer), which is valuable since there is no output schema, but it says nothing about behavior on unknown refs, errors, or whether statuses are live-updated.

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?

It is a single compact sentence with no filler, and the discriminating information (the two identifier options and returned fields) is front-loaded. However, the telegraphic, verbless style costs clarity relative to its brevity – 'who' and 'One checkout' are ambiguous enough that a few more words would have paid for themselves.

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 read-only lookup with no output schema and no annotation gaps, the essentials are nearly covered: what identifiers to pass and what fields come back. Missing are identifier formats, behavior when the ref is unknown or a checkout hasn't started, and any hint about the relationship to pay_checkout. Adequate but with clear gaps.

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 0% for the two optional string params, so the description carries real weight. It does communicate the key semantic that exactly one of session id or ref is supplied, and it names the field's conceptual identity, which compensates partially. It still gives no format or examples for either identifier, leaving the agent to guess what a valid ref looks like.

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 fragment 'One checkout (session id) or one ref' plus the status list conveys that this returns payment status, but it never names the verb (get/fetch) or states the resource explicitly, and it does not distinguish itself from siblings like pay_event, pay_checkout, or pay_payout_status. An agent can guess the purpose but must infer it from the field list rather than a stated operation.

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?

There is no guidance on when to call this versus pay_checkout, pay_event, order_status, or pay_payout_status. The only routing hint is internal to the tool (session vs ref), not about when the tool itself is appropriate.

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