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

Meaningfully supplements the annotations: it discloses a real side effect (the check 'may release the payment') and frames it as normal order progression, which explains why readOnlyHint is false despite a 'get'-style name. Rate limiting and the polling cadence are also called out, though auth/permission needs and failure behavior are not.

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?

Front-loaded with the return value and kept to three tight sentences. The 'that is the order proceeding, not an extra charge' clause is a worthwhile clarification rather than filler, though the phrasing is dense and fragments the flow slightly.

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?

An output schema exists, so return details need not be described, and the description covers the key behavioral risks (side effect, rate limit) for a polling tool. It could better position this against act_on_order, but nothing required to call it correctly is missing.

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 only 50% schema coverage, the description should carry more weight. It adds the semantics of the token ('the token's holder'), but orderId is unexplained in both places, and it references pollAfterSeconds, which is not an input parameter, creating a small ambiguity about what the caller actually supplies.

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 the resource ('an order's state') and what the caller gets back ('the next actions for the token's holder'), so an agent knows this is a status/next-action lookup. It does not directly name the sibling it differs from, e.g. act_on_order, leaving some differentiation to inference.

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 operational rule ('poll no faster than pollAfterSeconds') and clarifies the intended read of a payment release, but it never states when to prefer this over act_on_order or other order tools. Usage is implied rather than contrasted with alternatives.

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