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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description goes beyond them with "not counted as a visit to the record" and the not-found behavior for revoked links, both of which are non-obvious traits an agent could not infer from structured fields. It does not describe the shape of the returned record.

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 what the tool does, followed by access rules and the not-found case. Every sentence carries information, though "Reading changes nothing" partially overlaps the readOnlyHint annotation.

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 read tool with full annotation coverage and a fully documented schema, this covers purpose, access rules, and failure behavior. The only gap is the return value, which is acceptable given there is no output schema and the description does describe the resource as "the bank reports on a paid transfer".

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 100% for the single record_token parameter, including the max/min length and the note that either the token or the whole link is accepted. The description's phrase "from its link" merely echoes the schema, adding no new meaning; baseline 3 is appropriate.

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 uses a specific verb ("Read") plus resource ("a payment record") and frames it as link-scoped ("from its link"), which separates it from the broader get_transfer sibling. It never names that sibling explicitly, so the differentiation is implicit rather than stated.

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 access context ("Any key can read a record it has the link to, from any account") and notes the failure case for replaced or nonexistent links, which helps an agent decide when the call will succeed. It stops short of saying when to choose this over get_transfer or get_billing_link, so alternatives are left to inference.

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