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

With readOnlyHint=true and openWorldHint=false already declaring the safety profile, the description still adds real behavioural value: it discloses the return payload (intent, hash, every assumption made) despite no output schema, and states that the source currency is never assumed. It also flags that assumptions are surfaced rather than errors thrown. It stops short of describing behaviour on ambiguous or contradictory input.

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?

Three sentences, each carrying distinct information: what is captured, what input shapes are accepted, and what comes back. The artifact name and the accepted forms are front-loaded, and nothing is padded or restated from the schema verbatim.

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 ten-parameter, all-optional tool with a nested payer object and no output schema, the description covers the input variants, the output shape, and the non-defaulting rule for currency. What is missing is how it behaves when the sentence is under-specified enough that an assumption would be unsafe, and whether the returned intent is persisted or ephemeral.

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 schema already documents all ten parameters and the description earns baseline. It adds two things beyond the schema: a concrete worked example for the free-text 'text' input ('pay a Japanese supplier JPY 800m by 15 October') and the clarification that an omitted source currency is never silently defaulted, which matters for 'from'. The rest of the field list restates what the schema already says.

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 artifact: turn a corporate FX or payment requirement into a PaymentIntent, and enumerates what gets captured (currencies, amount + basis, value date, principal constraints). It is unmistakably the structuring step, but it never names the sibling it hands off to (decide_intent, route_intent, payment_intent), so differentiation rests on 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?

Usage is implied rather than stated: the tool accepts 'a sentence, a flat form, or a full intent', which tells the agent the input shapes but not when to prefer this over payment_intent, decide_intent or route_intent. 'Free' signals a no-cost first step, which hints at call-often behaviour, but there is no explicit when-not or prerequisite.

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