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

Annotations only declare the destructive/idempotent/read-write profile; the description supplies the substantive behavior behind it: a 3-correction quota shared with the website, whole-record replacement semantics, a no-op path that consumes no correction when details already match, and hard refusal conditions (archived transfer, checks ended before a report). The no-op rule is consistent with idempotentHint=true and the overwrite-with-quota rule is consistent with destructiveHint=true.

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?

The purpose is front-loaded and most sentences carry real information, but the sentence about copies already holding the details is convoluted and hard to parse, and 'Before a report, every save checks the transfer again' is vague about what is actually checked. Tightening these would materially improve readability.

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 destructive mutation with nested parameters, the description covers quota limits, authorization scope, refusal conditions, replacement semantics and a brief note on the return payload (transfer, outcome, corrections left), while the output schema carries return detail and annotations carry the safety profile. Nothing an agent needs to call it safely 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?

Schema coverage is 100%, so the baseline is 3; the description earns above that by clarifying that all three details must be supplied as they should stand and are replaced together, i.e. no partial updates — a constraint the required-array alone does not make obvious. It also states the UETR is immutable because it identifies the payment.

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 opening sentence names a specific verb and resource plus the exact fields in scope: 'Corrects the amount, currency or payment date entered for a transfer.' Combined with 'The UETR cannot be changed', it separates this tool from rename_transfer and recheck_transfer without the agent needing to open any schema.

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 unusually explicit when-and-when-not conditions: allowed after a bank report up to 3 corrections, shared with website corrections, refused once archived or when checks ended before any bank reported, and restricted to the owner's API keys and connected apps. The only gap is that it never names an alternative tool (e.g. rename_transfer for name changes, recheck_transfer for re-checks) to route the agent elsewhere.

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