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

With readOnlyHint already declaring it safe, the description still adds substantial context: the three possible row states and the full catalogue of failure reasons, the private signed record containing only a file hash and row states with no names or accounts, and the paid Authorization Bearer requirement. The 'never sends, holds or routes the money' statement removes any doubt about side effects on funds.

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 action and scope, then the input contract, then the outputs. The long reason enumeration is dense but each item tells the agent what a non-ok verdict can mean; the pricing sentence is short and last. Slight cost: the reason list reads as a run-on that could be structured more scannably.

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?

There is no output schema, so the description carries the return-value burden fully and does so: per-row ok/needs_person/blocked plus reasons, and the optional signed record. For a pre-flight validation tool with three plain parameters, nothing an agent needs before calling is absent.

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, but the description earns above it by specifying accepted input formats the schema only gestures at: pain.001 versions .03 to .12, and CSV with a header row using comma or semicolon and Dutch or English column names. It also implicitly clarifies 'today' by tying it to past-or-weekend execution-date rejections, though 'review_above' gets no extra detail beyond its schema text.

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: a pre-release check on an entire payout file, run before it reaches the company's bank or PSP. It also draws a hard boundary against the release/routing siblings by stating 'SwapEazi never sends, holds or routes the money', so an agent can tell it apart from run_payments or submit_payment without reading schemas.

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?

The temporal context is explicit ('before it goes to the company's own bank or PSP') and the non-action boundary rules out execution siblings. What's missing is a named alternative for the adjacent tasks (e.g. beneficiary-level checks like swapeazi_beneficiary_check) or an explicit 'do not use this for single payments' exclusion.

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