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

Annotations already declare readOnlyHint and idempotentHint, and the description adds substantial behavior beyond that: supplied inputs are echoed in `fields` and never re-asked, sensitive verticals yield a consult, EU+US scope triggers the EUR<->USD settlement corridor, and no provider/bank/acquirer is ever named. It also states clearly what is NOT returned (pricing, rates, bps, fees, savings).

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 front-loaded rule is good, but the opening two sentences restate the same condition ('which Crosswire products or rails fit their setup') three times, which is pure redundancy. The rest of the content earns its place, but the definition would be tighter without the repetition.

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 10-parameter tool with no output schema, the description covers the return shape (rails plus rationale plus source need), consult fallbacks, and the corridor addition. It is nearly complete, though the roles of `regions`, `target_launch`, and `monthly_volume` in shaping the recommendation are left implicit.

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 80%, so baseline is already 3, and the description adds genuine meaning on top: `description` is preferred over structured inputs, `optimise_for` re-sequences the same architecture without touching pricing, and `engagement_ref` is only honored when valid/unexpired/unrevoked. It does not explain `regions`, `target_launch`, or `monthly_volume` semantics, keeping it short of a 5.

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 ('Recommend a Crosswire stack') and immediately scopes it against its closest sibling by naming `get_indicative_price` as the wrong tool for pricing questions. An agent can distinguish this from `design_stack` or `compare_stack_scenarios` on the basis of the recommendation-vs-pricing axis.

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 rule for both directions: use when the user asks which products/rails fit their setup, and use `get_indicative_price` instead for any price/rate/cost/fee question. It also carves out sensitive verticals (forex, adult) that return a consult rather than a firm stack, which is real routing guidance.

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