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

Adds real disclosure beyond the annotations: the tool reads only this service's own record, never the seller or the chain, which explains the openWorldHint=false boundary and warns against treating a miss as proof of failure. The confidentiality note ('whoever holds the reference can read it, keep it private') is valuable, non-obvious behavior. It stops short of describing what states can be returned or what an unknown reference yields.

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?

Four short sentences, front-loaded with the core action and reference provenance, then the read-scope caveat, then the security warning. Nothing is padded; 'read-only and free' is the only near-duplication of the annotations and it adds the cost fact.

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 one-parameter, no-output-schema tool the description covers invocation and trust boundaries well, but leaves the return shape undefined: an agent cannot tell what state values to expect or how an unknown/pending reference is represented. That gap matters precisely because there is no output schema to fall back on.

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% – the reference parameter has no description or format guidance in the schema. The description compensates well by explaining where the reference comes from and treating it as the sole access key, but does not mention the 36-character cap or expected format.

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 ('Show the state of a payment') plus the exact provenance of the identifier ('made with listing_pay, by the reference that listing_pay gave you'). This cleanly separates it from the sibling listing_pay (which creates the payment) and from the marketplace_* lookup tools.

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?

Gives an explicit precondition (a reference produced by listing_pay), an explicit availability note ('read-only and free'), and an explicit when-not path: for an unknown or pending payment, verify on-chain yourself before paying again. That is the alternative-action guidance an agent needs, with no inference required.

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